WO2022170806A1

WO2022170806A1 - Mapping method and apparatus, navigation method and apparatus, electronic device, and readable storage medium

Info

Publication number: WO2022170806A1
Application number: PCT/CN2021/131528
Authority: WO
Inventors: 刘烨航; 成鹏; 张广鹏; 王旭
Original assignee: 灵动科技（北京）有限公司
Priority date: 2021-02-09
Filing date: 2021-11-18
Publication date: 2022-08-18
Also published as: CN114911882A

Abstract

Disclosed in embodiments of the present disclosure are a mapping method and apparatus, a navigation method and apparatus, an electronic device, and a readable storage medium. The mapping method comprises: a node dividing step, wherein a first region is divided into nodes; a node state and position obtaining step, wherein the states and positions of the nodes are obtained; a semantic tag obtaining step, wherein a semantic tag is obtained according to the nodes in the first region; and a semantic tag state obtaining step, wherein the first state and/or the second state of the semantic tag is obtained, the first region being is a region that may be occupied by a mobile device in a specific region. Thus, accurate division on a region and complete marking of states are performed, detailed semantic analysis is performed, and adaptation to changes in a scene is implemented, thereby facilitating flexible scheduling of the mobile device.

Description

Map construction and navigation method, apparatus, electronic device and readable storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application number "CN 202110179020.X" filed on February 9, 2021, the entire contents of which are incorporated into this application as a whole.

technical field

The present disclosure relates to the technical field of navigation, and in particular, to a map construction and navigation method, apparatus, electronic device, and readable storage medium.

Background technique

In the field of navigation, how to design a map that represents the environment and navigate the mobile device in the map is an important and critical issue. Simultaneous Localization And Mapping (SLAM) is the most commonly used method of map construction. It usually collects and calculates data through various sensors on robots or other carriers to generate localization and scene maps of its own position and attitude. information.

In the patent document CN110807782A "A Map Representation System for Visual Robot and Its Construction Method", the scene map is constructed by means of geometry and topology, but the semantic analysis of the scene is not sufficient, and it cannot deal with complex scenes, nor does it propose The method of navigation combined with map semantics results in a large subsequent scheduling overhead and does not have scheduling flexibility for changing scenarios.

SUMMARY OF THE INVENTION

In order to solve the problems in the related art, the embodiments of the present disclosure provide a map construction and navigation method, an apparatus, an electronic device, and a readable storage medium.

In a first aspect, an embodiment of the present disclosure provides a map construction method, including: a node division step, wherein a first area is divided into nodes;

a node state and position acquisition step, wherein the state and position of the node are acquired;

A semantic label acquiring step, wherein a semantic label is acquired according to the node in the first area;

The step of obtaining the semantic label state, wherein the first state and/or the second state of the semantic label is obtained,

The first area is an area in a specific area that can be occupied by a mobile device.

With reference to the first aspect, in a first implementation manner of the first aspect of the present disclosure, the node division step includes:

The first area is divided into the nodes according to the area perceived by the mobile device and/or the area occupied by the mobile device.

In conjunction with the first aspect, the present disclosure is in a second implementation manner of the first aspect,

obtaining the location of the node using a simultaneous localization and mapping method; and/or

The state of the node is obtained using a visual method.

In conjunction with the first aspect, in a third implementation manner of the first aspect of the present disclosure, the state of the node includes:

Occupied state, not occupied state.

In conjunction with the third implementation manner of the first aspect, the present disclosure is in the fourth implementation manner of the first aspect, and the semantic label obtaining step includes:

The semantic labels are obtained using a clustering method according to the states and positions of the nodes in the first region.

In conjunction with the first aspect, in a fifth implementation manner of the first aspect of the present disclosure, the first state of the semantic tag includes:

unblocked state, crowded state, jammed state; and/or

The second state of the semantic tag includes:

Locked state, unlocked state.

With reference to the fifth implementation manner of the first aspect, in the sixth implementation manner of the present disclosure, in the semantic label, the consecutive nodes connecting both sides of the semantic label are all in the occupied state. , the first state of the semantic label is the blocked state;

Under the condition that the number of the nodes in the occupied state in the semantic label is greater than a first threshold, or the proportion of the nodes in the occupied state in the semantic label is greater than a second threshold, the semantic The first state of the tag is the congestion state.

With reference to the fifth implementation manner of the first aspect, in the seventh implementation manner of the first aspect of the present disclosure, the first state of the semantic label is a smooth state, or the first state of the semantic label is a crowded state and under the condition that the congestion index is less than or equal to the third threshold, the second state of the semantic label is an unlocked state;

The second state of the semantic label is locked when the first state of the semantic label is a congestion state, or the first state of the semantic label is a crowded state and the congestion index is greater than the third threshold state.

In a second aspect, an embodiment of the present disclosure provides a method for navigating a mobile device according to the map construction method of any one of the first aspect to the seventh implementation manner of the first aspect, including:

a navigation start and end position obtaining step, wherein the navigation start position and the navigation end position of the mobile device are obtained;

Navigation path planning step, wherein based on the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node are calculated navigation path;

A moving step, wherein the mobile device is controlled to move along the navigation path;

A state update step, wherein the state of the node, the first state of the semantic label and/or the second state of the semantic label are updated according to the location of the mobile device and/or the detection result of the mobile device ;

A navigation path update step, wherein the navigation path is updated according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node .

With reference to the second aspect, in a first implementation manner of the second aspect of the present disclosure, the navigation path planning step includes:

Under the condition that the navigation start position and the navigation end position are within the same semantic label, the navigation path is calculated using a topology-graph level path planning algorithm;

Under the condition that the navigation start position and the navigation end position are not within the same semantic label, the navigation path is calculated using a semantic label-level path planning algorithm.

In a third aspect, an embodiment of the present disclosure provides a map construction apparatus, including:

a node division module, configured to divide the first area into nodes;

a node state and location acquisition module, configured to acquire the state and location of the node;

a semantic label obtaining module, configured to obtain a semantic label according to the node in the first area;

a semantic tag state acquisition module, configured to acquire the first state and/or the second state of the semantic tag,

With reference to the third aspect, in a first implementation manner of the third aspect of the present disclosure, the node division module is further configured to:

According to the area perceived by the mobile device and/or the area occupied by the mobile device, an area that may be occupied by the mobile device in the first area is divided into the nodes.

In conjunction with the third aspect, in a second implementation manner of the third aspect, the present disclosure uses a simultaneous positioning and mapping method to obtain the location of the node; and/or

The state of the node is obtained using a visual method.

In conjunction with the third aspect, in a third implementation manner of the third aspect of the present disclosure, the state of the node includes:

Occupied state, not occupied state.

With reference to the third implementation manner of the third aspect, in a fourth implementation manner of the third aspect of the present disclosure, the semantic tag obtaining module is further configured to:

In conjunction with the third aspect, in a fifth implementation manner of the third aspect of the present disclosure, the first state of the semantic tag includes:

unblocked state, crowded state, jammed state; and/or

The second state of the semantic tag includes:

Locked state, unlocked state.

In conjunction with the fifth implementation manner of the third aspect, the present disclosure is in the sixth implementation manner of the third aspect,

Under the condition that the continuous nodes connecting both sides of the semantic label in the semantic label are in the occupied state, the first state of the semantic label is the blocked state;

In conjunction with the fifth implementation manner of the third aspect, the present disclosure is in the seventh implementation manner of the third aspect,

Under the condition that the first state of the semantic label is the unblocked state, or the first state of the semantic label is the crowded state and the congestion index is less than or equal to the third threshold, the second state of the semantic label is the unlocked state ;

In a fourth aspect, an embodiment of the present disclosure provides a mobile device navigation apparatus of the map construction apparatus according to any one of the third aspect to the seventh implementation manner of the third aspect, including:

a navigation start and end position acquisition module, configured to acquire a navigation start position and a navigation end position of the mobile device;

A navigation path planning module configured to base on the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node Calculate the navigation path;

a movement module configured to control the mobile device to move along the navigation path;

A state update module, configured to update the state of the node, the first state of the semantic label and/or the second state of the semantic label according to the location of the mobile device and/or the detection result of the mobile device state;

A navigation path update module configured to update the navigation according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node path.

In conjunction with the fourth aspect, in a first implementation manner of the fourth aspect of the present disclosure, the navigation path planning module is further configured to:

In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor; wherein,

The memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the first aspect, the first implementation manner to the ninth implementation of the first aspect The method of any one of the methods.

In a sixth aspect, an embodiment of the present disclosure provides a readable storage medium on which computer instructions are stored, and when the computer instructions are executed by a processor, implement the first aspect, the first implementation manner of the first aspect to the sixth aspect. The method described in any one of the nine implementation manners.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

According to an embodiment of the present disclosure, through a node division step, in which the first area is divided into nodes; a node state and position acquisition step, in which the state and position of a node are acquired; and a semantic label acquisition step, in which according to the first area The node of the node obtains the semantic label; the step of obtaining the semantic label state, in which the first state and/or the second state of the semantic label is obtained, and the first area is the area that may be occupied by the mobile device in the specific area, so as to accurately divide the area and determine the state. Complete markup, detailed semantic analysis, and adapt to scene changes, facilitating flexible scheduling of mobile devices.

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

Description of drawings

Other features, objects and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the attached image:

Fig. 1a shows an exemplary schematic diagram of an implementation scenario of a map construction method according to an embodiment of the present disclosure;

Fig. 1b shows an exemplary schematic diagram of an implementation scenario of a map construction method according to an embodiment of the present disclosure;

Fig. 1c shows an exemplary schematic diagram of an implementation scenario of a navigation method according to an embodiment of the present disclosure;

Fig. 1d shows an exemplary schematic diagram of an implementation scenario of a navigation method according to an embodiment of the present disclosure;

FIG. 2 shows a flowchart of a map construction method according to an embodiment of the present disclosure;

FIG. 3 shows a flowchart of a navigation method according to an embodiment of the present disclosure;

4 shows a structural block diagram of a map construction apparatus according to an embodiment of the present disclosure;

FIG. 5 shows a structural block diagram of a navigation device according to an embodiment of the present disclosure;

6 shows a structural block diagram of an electronic device according to an embodiment of the present disclosure;

Fig. 7 is a schematic structural diagram of a computer system suitable for implementing a map construction method and a navigation method according to an embodiment of the present disclosure.

Detailed ways

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts unrelated to describing the exemplary embodiments are omitted from the drawings.

In the present disclosure, it should be understood that terms such as "comprising" or "having" are intended to indicate the presence of labels, numbers, steps, acts, components, parts, or combinations thereof disclosed in this specification, and are not intended to exclude a or multiple other labels, numbers, steps, acts, parts, sections, or combinations thereof may exist or be added.

In addition, it should be noted that the embodiments in the present disclosure and the tags in the embodiments may be combined with each other under the condition of no conflict. The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

In order to solve the above problems, the present disclosure proposes a map construction and navigation method, apparatus, electronic device and readable storage medium.

Fig. 1a shows an exemplary schematic diagram of an implementation scenario of a map construction method according to an embodiment of the present disclosure.

Those of ordinary skill in the art can understand that FIG. 1a exemplarily shows an implementation scenario of the map construction method, and does not constitute a limitation to the present disclosure.

As shown in FIG. 1a , in a specific area 100, such as a warehouse, surrounded by endpoints ABCD, there are rack 1, rack 2, rack 3, rack 4, rack 5, and rack 6. A mobile device such as an automatic handling robot can move in an area other than the shelves in the warehouse, that is, the first area, and complete the access operation to the goods on the shelves.

In the embodiment of the present disclosure, the first area may be divided into nodes according to an area that an automatic handling robot can perceive, or an area occupied by an automatic handling robot. For example, node 101 in Figure 1a. The node 101 may be an idle upper space 1 and an upper space 2, or may be a parking space 1 left 4 occupied by an automatic handling robot. In Figure 1a and the following Figures 1b to 1d, the nodes occupied by the automatic handling robot are marked in gray. Through the above method of dividing nodes, a number of nodes are divided in the first area, for example, the upper position 1...the upper position 9, the left position 1-1...the left position 1-16, the main road 1-2 ...arterial road 113 etc. The perception of the automatic handling robot may be tactile perception of a robotic arm, or ultrasonic perception, or other perception methods, which are not limited in the present disclosure.

In Figure 1a, the position of the node can be obtained using a positioning method such as a synchronous Location and Mapping (SLAM) method, and the state of the node can be obtained using a visual method such as machine vision of an automatic handling robot, such as a node occupied state. The automatic handling robot can also identify that the node is in an occupied state by being in a certain node.

In the embodiment of the present disclosure, the state information of the nodes may also include the state information of adjacent nodes, so as to facilitate the overall analysis of the multiple nodes and facilitate the movement of the automatic handling robot.

Those skilled in the art can understand that the specific area 100 may be other areas such as a production workshop in addition to a warehouse, and the first area that the automatic handling robot can occupy may vary with the position of the shelves in the warehouse or the production line in the production workshop. Changes may occur due to adjustments, etc., which are not limited in the present disclosure. In addition to an automatic handling robot, the mobile device may also be other mobile devices such as an automatic forklift, an automatic detection robot, etc., which is not limited in the present disclosure. In addition to the SLAM method, methods such as ultrasound and wireless positioning can also be used to obtain the location of the node, which is not limited in the present disclosure.

Fig. 1b shows an exemplary schematic diagram of an implementation scenario of a map construction method according to an embodiment of the present disclosure.

Those of ordinary skill in the art can understand that FIG. 1b exemplarily shows an implementation scenario of the map construction method, and does not constitute a limitation to the present disclosure.

As shown in Figure 1b, a clustering method such as K-means clustering can be used to cluster the nodes in Figure 1a to obtain semantic labels. The resulting semantic labels can be upper channel 111, lower channel 112, left channel 1 1131, left channel 2 1132, road 1 1141, road 2 1142, road 3 1143, road 4 1144, right channel 1 1151, right channel 2 1152 .

In an embodiment of the present disclosure, the first state of the semantic label may include: a clear state, a congested state, and a blocked state. For example, no node in the left channel 1 1131 is in the occupied state, the first state of the left channel 1 1131 is the unblocked state; the continuous nodes 1171 and 1172 on both sides of the roadway 4 1144 are in the occupied state, and the first state of the roadway 4 1144 is in the occupied state. is a blocked state. The 5 nodes 1161, 1162, 1163, 1164, and 1165 in the roadway 3 1143 are in an occupied state, and the number of nodes in the occupied state is greater than the first threshold such as 3, and the first state of the roadway 3 1143 is a crowded state. The first state of the semantic label is used to identify the congestion level of the semantic label.

In the embodiment of the present disclosure, the proportion of nodes in the occupied state in the semantic label may also be greater than the second threshold, for example, greater than 1/4, so as to determine that the first state of the semantic label is the crowded state.

In the embodiment of the present disclosure, the handling robot may be scheduled to pass the semantic label of the unblocked state first, and then the handling robot may be scheduled to pass the semantic label of the crowded state. For the semantic label in the blocked state, the handling robot may not be scheduled to pass through.

In an embodiment of the present disclosure, the second state of the semantic tag may include a locked state and an unlocked state. Semantic tags in unlocked state can be scheduled, but semantic tags in locked state cannot be scheduled.

In the embodiment of the present disclosure, under the condition that the first state of the semantic label is the unblocked state, the second state of the semantic label is the unlocked state. Under the condition that the first state of the semantic label is the blocked state, the second state of the semantic label is the locked state. Under the condition that the first state of the semantic label is a crowded state, and the congestion index is less than or equal to a third threshold such as 0.2, the second state of the semantic label is an unlocked state; the first state of the semantic label is a crowded state, and the crowded state The second state of the semantic label is a locked state under the condition that the index is greater than a third threshold, eg, 0.2.

In the embodiment of the present disclosure, the second state of the left lane 1 1131 is an unlocked state and can be scheduled by navigation; the second state of the lane 41144 is a locked state and cannot be scheduled by navigation. Although the roadway 3 1143 is not completely blocked, there are many nodes in the occupied state, and the congestion index is greater than the third threshold. It is difficult for the subsequent handling robot to pass through. The second state is the locked state and cannot be navigated and dispatched.

Those of ordinary skill in the art can understand that, in addition to K-means clustering, mean shift clustering, density-based clustering, or other clustering methods can also be used to obtain semantic labels from nodes, which are not limited in this disclosure. The third threshold may also be other values, which are not limited in the present disclosure.

Those of ordinary skill in the art can understand that changes occur with changes in the positions of shelves in the warehouse or adjustments of production lines in the production workshop, etc., as well as the movement of mobile equipment and/or the movement of people in the warehouse and production workshop, etc., the node status , the status of semantic tags can be changed.

Fig. 1c shows an exemplary schematic diagram of an implementation scenario of a navigation method according to an embodiment of the present disclosure.

Those skilled in the art can understand that FIG. 1c exemplarily shows an implementation scenario of the navigation method, and does not constitute a limitation to the present disclosure.

As shown in FIG. 1 c , the transfer robot A starts from the node 121 and needs to access the goods at the node 122 or 123 . For example, the handling robot needs to store goods, and the shelf positions corresponding to nodes 122 and 123 have suitable free storage spaces; or the handling robot needs to take out the goods a, and the shelf positions corresponding to the nodes 122 and 123 both store the goods a.

In the embodiment of the present disclosure, in the navigation task, the navigation start position may be node 121 , and the navigation end position may be node 122 or 123 . Since the semantic label lane 3 1143 where the node 123 is located is in a congested state and locked state and cannot be scheduled, node 122 is selected as the final navigation termination position. According to the first state and the second state of each semantic label, and the state and position of each node, the navigation path 124 is calculated as: left channel 2 1132--> main road 113--> left channel 11131--> upper channel 111-- > Lane 2 1142.

In the embodiment of the present disclosure, under the condition that the navigation start position and the navigation end position are within different semantic labels, for example, the aforementioned navigation start position is node 121, which is located in the lower channel 112, and the navigation end position is node 122. Located in the upper channel 111, the navigation path can be calculated using a semantic tag-level path planning algorithm. The semantic label-level path planning algorithm may use, for example, the topological connection relationship between semantic labels to perform computation, or other relationships between semantic labels to perform computation.

Fig. 1d shows an exemplary schematic diagram of an implementation scenario of a navigation method according to an embodiment of the present disclosure.

Those of ordinary skill in the art can understand that FIG. 1d exemplarily shows an implementation scenario of the navigation method, and does not constitute a limitation to the present disclosure.

As shown in Fig. 1d, when the handling robot A moves to the node 131, the node 132 of the channel 1 1131 on the left side of the semantic label is occupied by the handling robot B and is in an occupied state. At this time, the first state of the channel 1 1131 on the left side of the semantic label is updated to the blocked state, the second state is updated to the locked state, and the handling robot A cannot move according to the original navigation path 124 in FIG. 1c. According to the first state and second state of each semantic label, as well as the state and position of each node, the navigation path of the updated handling robot A is 133: left channel 2 1132 --> main road 113 --> roadway 2 1142. When the handling robot A is at node 131 and the navigation end position is at node 122, node 131 and node 122 are not in the same semantic label, and a semantic label-level path planning algorithm is used to plan the route. When the handling robot A moves to the semantic label lane 2 1142 along the navigation path 133, the node where the handling robot A is located and the navigation termination position are within the same semantic label, and the navigation path can be calculated by using a topology-level path planning algorithm. The topology-graph-level path planning algorithm can perform computation by using, for example, the topological connection relationship between nodes in the semantic label, or other topological relationships.

The transfer robot A finally moves along the updated navigation path 133, reaches the node 122, and completes the access to the goods.

Those of ordinary skill in the art can understand that the node 132 of the channel 1 1131 on the left side of the semantic label in FIG. 1d is occupied by the handling robot B and is in an occupied state, which may be detected by the handling robot A or marked by the handling robot B. The calculation and update of the navigation path in Figure 1c and Figure 1d can be completed by each handling robot according to the state of the semantic label, the state and position of the node, and autonomously control the movement; it can also be controlled by the central control system of multiple handling robots. After the calculation is completed, each transport robot is controlled to move, which is not limited in the present disclosure.

FIG. 2 shows a flowchart of a map construction method according to an embodiment of the present disclosure.

As shown in Fig. 2, the map construction method includes steps S201, S202, S203, and S204.

In step S201, the first area is divided into nodes.

In step S202, the state and position of the node are acquired.

In step S203, a semantic label is acquired according to the nodes in the first area.

In step S204, the first state and/or the second state of the semantic tag is acquired.

The first area is an area in a particular area that can be occupied by a mobile device.

In an embodiment of the present disclosure, the first area may be an area in the warehouse area 100 shown in FIG. 1a that may be occupied by mobile devices such as automatic handling robots other than the shelves. The first area can be divided into nodes, for example, the upper position 1...the upper position 9, the left position 1-1...the left position 1-16, the main road 1-2...the main road 113, etc., and get the state and position of the node. The semantic label may be obtained according to the nodes in the first area, for example, by aggregating the nodes to obtain the semantic label. Semantic labels can be various channels shown in Figure 1b, such as upper channel 111, left channel 1 1131, main road 113, etc. The first state and/or the second state of the semantic label can be acquired, the first state is used to identify the congestion level of the semantic label, and the second state is used to identify whether the semantic label is locked, and further whether it can be navigated and scheduled.

According to an embodiment of the present disclosure, through a node division step, in which the first area is divided into nodes; a node state and position acquisition step, in which the state and position of a node are acquired; and a semantic label acquisition step, in which according to the first area The node of the node obtains the semantic label; the step of obtaining the semantic label state, wherein the first state and/or the second state of the semantic label is obtained, and the first area is the area that can be occupied by the mobile device in a specific area, so as to accurately divide the area and determine the state. Complete markup, detailed semantic analysis, and adapt to scene changes, facilitating flexible scheduling of mobile devices.

In the embodiment of the present disclosure, the first area may be divided into nodes according to the area sensed by the mobile device, eg, tactile perception, ultrasonic perception, and/or the area occupied by the mobile device.

According to an embodiment of the present disclosure, the step of dividing the nodes includes: dividing the first area into nodes according to the area perceived by the mobile device and/or the area occupied by the mobile device, so as to accurately divide the area and complete the marking of the state, and carry out detailed Semantic analysis, and adapt to changes in the scene, to facilitate flexible scheduling of mobile devices.

In the embodiment of the present disclosure, the position of the node may be acquired by, for example, a simultaneous localization and mapping (SLAM) method, and the state of the node may be acquired by a visual method.

According to an embodiment of the present disclosure, the position of the node is obtained by using a simultaneous localization and mapping method; and/or the state of the node is obtained by using a visual method, so as to accurately divide the area and complete the marking of the state, perform detailed semantic analysis, and Adapt to changes in the scene and facilitate flexible scheduling of mobile devices.

Those of ordinary skill in the art can understand that other positioning methods such as ultrasound and wireless positioning can also be used to obtain the node position, and the mobile device can also identify the state of the node according to its own position, which is not limited in the present disclosure.

In the embodiment of the present disclosure, the node state may include: an occupied state and a non-occupied state. The occupancy status of a node may be occupied by a mobile device, or occupied by a person, or occupied by temporarily placed goods, etc., which is not limited in the present disclosure.

According to the embodiments of the present disclosure, the states of the nodes include: occupied state and non-occupied state, so as to accurately divide the area and complete the state mark, carry out detailed semantic analysis, and adapt to the change of the scene, so as to facilitate the flexibility of the mobile device. schedule.

In the embodiment of the present disclosure, a method such as K-means clustering may be adopted, and a semantic label may be obtained by using the clustering method according to the state and position of the nodes in the first area.

According to an embodiment of the present disclosure, the step of obtaining semantic labels includes: according to the states and positions of nodes in the first area, using a clustering method to obtain semantic labels, so as to accurately divide the area and complete the labeling of the state, and perform detailed semantic Analysis, and adapt to changes in the scene, to facilitate flexible scheduling of mobile devices.

Those of ordinary skill in the art can understand that, in addition to K-means clustering, mean shift clustering, density-based clustering, or other clustering methods can also be used to obtain semantic labels from nodes, which are not limited in this disclosure.

In the embodiment of the present disclosure, the first state of the semantic label includes: a clear state, a congested state, and a blocked state; the second state of the semantic label includes: a locked state and an unlocked state. Semantic tags in congestion state cannot be scheduled, semantic tags in unblocked state are scheduled first, and semantic tags in congested state are scheduled second. Semantic tags in the locked state are not scheduled, and semantic tags in the unlocked state can be scheduled.

According to an embodiment of the present disclosure, the first state of the semantic label includes: a clear state, a crowded state, and a blocked state; and/or the second state of the semantic label includes: a locked state and an unlocked state, so that the region can be precisely calibrated. Complete labeling of partitions and states, detailed semantic analysis, and adaptation to scene changes, facilitating flexible scheduling of mobile devices.

In the embodiment of the present disclosure, as shown in FIG. 1b, the continuous nodes 1171 and 1172 on both sides of the roadway 4 1144 are in the occupied state, and the first state of the roadway 4 1144 is the blocked state. The 5 nodes 1161, 1162, 1163, 1164, and 1165 in the roadway 3 1143 are in an occupied state, and the number of nodes in the occupied state is greater than the first threshold such as 3, and the first state of the roadway 3 1143 is a crowded state. The first state of the semantic label is used to identify the congestion level of the semantic label.

According to an embodiment of the present disclosure, the first state of the semantic label is the blocked state by the condition that the continuous nodes connecting both sides of the semantic label in the semantic label are in the occupied state; the number of nodes in the occupied state in the semantic label If it is greater than the first threshold, or the proportion of nodes in the occupied state in the semantic label is greater than the second threshold, the first state of the semantic label is a crowded state, so that the region can be accurately divided and the state is fully marked, and detailed semantics can be carried out. Analysis, and adapt to changes in the scene, to facilitate flexible scheduling of mobile devices.

In the embodiment of the present disclosure, the first state is in the congestion state, or the second state of the semantic label in the congestion state and the congestion index is greater than a third threshold such as 0.2 is the locked state; the first state is in the unblocked state, or in the congestion state The second state of the semantic label with a congestion index less than or equal to a third threshold, eg, 0.2, is an unlocked state. The third threshold may also be other values, which are not limited in the present disclosure.

According to an embodiment of the present disclosure, the second state of the label is unlocked by the condition that the first state of the semantic label is the unblocked state, or the first state of the semantic label is the congested state and the congestion index is less than or equal to the third threshold state; under the condition that the first state of the semantic label is a blocked state, or the first state of the semantic label is a crowded state and the congestion index is greater than the third threshold, the second state of the semantic label is a locked state, so as to accurately divide the area It can perform detailed semantic analysis and adapt to changes in the scene to facilitate flexible scheduling of mobile devices.

FIG. 3 shows a flowchart of a navigation method according to an embodiment of the present disclosure.

Specifically, FIG. 3 shows a method for navigating a mobile device according to FIG. 2 and the aforementioned map construction method.

As shown in FIG. 3 , the navigation method includes steps S301 , S302 , S303 , S304 and S305 .

In step S301, a navigation start position and a navigation end position of the mobile device are acquired.

In step S302, the navigation path is calculated according to the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label.

In step S303, the mobile device is controlled to move along the navigation path.

In step S304, the state of the node, the first state of the semantic label and/or the second state of the semantic label are updated according to the location of the mobile device and/or the detection result of the mobile device.

In step S305, the navigation path is updated according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label.

In the embodiment of the present disclosure, as shown in FIG. 1 c , the automatic handling robot A starts from the node 121 and needs to access the goods at the node 122 or 123 . According to the first state and the second state of each semantic label, as well as the state and position of each node, the node 122 is selected as the navigation termination position, and the navigation path 124 is calculated as: left channel 2 1132 --> main road 113 --> left Channel 1 1131-->The upper channel 111--> Lane 2 1142. As shown in Fig. 1d, when the handling robot is controlled to move to the node 131, the node 132 is occupied by the automatic handling robot B, which causes the left channel 1 1131 to be blocked and locked, thereby updating the navigation path of the automatic handling robot A to 133. The automatic handling robot A moves to the node 122 along the new navigation path 133 to complete the access to the goods.

According to an embodiment of the present disclosure, the navigation start and end position acquisition steps are performed, wherein the navigation start position and the navigation end position of the mobile device are acquired; the navigation path planning step, wherein, according to the navigation start position, the navigation end position, the first position of the semantic label is obtained. A state and/or a second state of the semantic label, and the state and position of the node to calculate a navigation path; a moving step, in which the mobile device is controlled to move along the navigation path; a state update step, in which the mobile device is moved according to the position and/or movement The detection result of the device, the state of the updated node, the first state of the semantic label and/or the second state of the semantic label; the navigation path update step, wherein, according to the updated state of the node, the first state of the semantic label and/or The second state of the semantic label, and the state and position of the node update the navigation path, so that based on the map of precise area division, state marking and semantic analysis, the mobile path of the mobile device can be flexibly scheduled, and can adapt to the dynamic changes of the scene.

In the embodiment of the present disclosure, as shown in FIG. 1c , under the condition that the navigation start position, node 121 and navigation end position, and node 122 of the automatic handling robot A are in different semantic labels, the semantic label-level path planning is adopted. The algorithm calculates the navigation path 124 . The semantic label-level path planning algorithm may use, for example, the topological connection relationship between semantic labels to perform computation, or other relationships between semantic labels to perform computation.

As shown in Figure 1d, after the automatic handling robot A moves to the semantic label lane 2 1142, the node where the automatic handling robot A is located, the navigation termination position and the node 122 are in the same semantic label, and the topology graph level path planning algorithm is used to calculate Navigation path. The topology-graph-level path planning algorithm can perform calculation by using, for example, the topological connection relationship between nodes in the same semantic label, or other topological relationships.

According to an embodiment of the present disclosure, the step of planning through the navigation path includes: on the condition that the navigation start position and the navigation end position are within the same semantic label, use a topology-graph level path planning algorithm to calculate the navigation path; Under the condition that the navigation termination position is not within the same semantic tag, the navigation path is calculated by using a semantic tag-level path planning algorithm, so that the movement path of the mobile device can be flexibly based on the map of precise area division, state marking and semantic analysis. Scheduling, and can adapt to the dynamic changes of the scene.

FIG. 4 shows a structural block diagram of a map construction apparatus according to an embodiment of the present disclosure.

As shown in FIG. 4 , the map construction apparatus 400 includes: a node division module 401 , a node state and position acquisition module 402 , a semantic label acquisition module 403 , and a semantic label state acquisition module 404 .

The node division module 401 is configured to divide the first area into nodes.

The node state and location acquisition module 402 is configured to acquire the state and location of the node.

The semantic label obtaining module 403 is configured to obtain semantic labels according to the nodes in the first area.

The semantic tag state acquisition module 404 is configured to acquire the first state and/or the second state of the semantic tag.

According to an embodiment of the present disclosure, the node dividing module is configured to divide the first area into nodes; the node status and position acquisition module is configured to acquire the status and position of the node; the semantic label acquisition module is configured to A node in an area obtains a semantic label; the semantic label state obtaining module is configured to obtain the first state and/or the second state of the semantic label, and the first area is an area that can be occupied by a mobile device in a specific area, so as to accurately perform the area Complete labeling of partitions and states, detailed semantic analysis, and adaptation to scene changes, facilitating flexible scheduling of mobile devices.

In the embodiment of the present disclosure, the node dividing module is further configured to: divide an area possibly occupied by the mobile device in the first area into the nodes according to the area perceived by the mobile device and/or the area occupied by the mobile device.

According to an embodiment of the present disclosure, the node dividing module is further configured to: divide the area possibly occupied by the mobile device in the first area into the nodes according to the area perceived by the mobile device and/or the area occupied by the mobile device, so as to divide the area into the nodes. Perform precise division and complete state labeling, perform detailed semantic analysis, and adapt to changes in scenarios to facilitate flexible scheduling of mobile devices.

FIG. 5 shows a structural block diagram of a navigation device according to an embodiment of the present disclosure.

Specifically, FIG. 5 shows an apparatus for navigating a mobile device according to FIG. 4 and the aforementioned map construction apparatus.

As shown in FIG. 5 , the navigation device 500 includes: a navigation start and end position acquisition module 501 , a navigation path planning module 502 , a movement module 503 , a state update module 504 , and a navigation path update module 505 .

The navigation start and end position obtaining module 501 is configured to obtain the navigation start position and the navigation end position of the mobile device.

The navigation path planning module 502 is configured to use the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node Calculate the navigation path.

The moving module 503 is configured to control the mobile device to move along the navigation path.

The state update module 504 is configured to update the state of the node, the first state of the semantic label and/or the second state of the semantic label according to the location of the mobile device and/or the detection result of the mobile device state.

The navigation path update module 505 is configured to update the navigation according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node path.

According to an embodiment of the present disclosure, the navigation start and end position acquisition module is configured to acquire the navigation start position and the navigation end position of the mobile device; the navigation path planning module is configured to obtain the navigation start position, navigation end position, semantic label according to the navigation start position, navigation end position The first state of the first state and/or the second state of the semantic label, and the state and position of the node calculate the navigation path; the moving module is configured to control the mobile device to move along the navigation path; the state update module is configured to be based on the position of the mobile device. And/or the detection result of the mobile device, update the state of the node, the first state of the semantic label and/or the second state of the semantic label; the navigation path update module is configured to update the node according to the updated state. state, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node update the navigation path, so that the movement path of the mobile device is based on the map of accurate division of regions, state marking and semantic analysis. Perform flexible scheduling and adapt to dynamic changes in the scene.

FIG. 6 shows a structural block diagram of an electronic device according to an embodiment of the present disclosure.

Embodiments of the present disclosure further provide an electronic device. As shown in FIG. 6 , the electronic device 600 includes a processor 601 and a memory 602; wherein, the memory 602 stores instructions that can be executed by at least one processor 601, and the instructions are At least one processor 601 executes to implement the following steps: a node division step, wherein the first area is divided into nodes;

In an embodiment of the present disclosure, the node division step includes:

In an embodiment of the present disclosure, the location of the node is obtained using a simultaneous positioning and mapping method; and/or

The state of the node is obtained using a visual method.

In the embodiment of the present disclosure, the status of the node includes:

Occupied state, not occupied state.

In the embodiment of the present disclosure, the step of acquiring the semantic label includes:

In an embodiment of the present disclosure, the first state of the semantic label includes:

unblocked state, crowded state, jammed state; and/or

The second state of the semantic tag includes:

Locked state, unlocked state.

In the embodiment of the present disclosure, under the condition that the continuous nodes connecting both sides of the semantic label in the semantic label are in the occupied state, the first state of the semantic label is the blocked state;

In the embodiment of the present disclosure, under the condition that the first state of the semantic label is an unblocked state, or the first state of the semantic label is a crowded state and the congestion index is less than or equal to a third threshold, the semantic label The second state of is an unlocked state;

The instructions may also be executed by at least one processor 601 to implement the following steps:

In an embodiment of the present disclosure, the navigation path planning step includes:

As shown in FIG. 7, a computer system 700 includes a processing unit 701 that can execute the above-mentioned appendixes according to a program stored in a read only memory (ROM) 702 or a program loaded from a storage section 708 into a random access memory (RAM) 703 Various processes in the embodiment shown in the figure. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The processing unit 701 , the ROM 702 and the RAM 703 are connected to each other through a bus 704 . An input/output (I/O) interface 705 is also connected to bus 704 .

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc. ; and a communication section 709 including a network interface card such as a LAN card, a modem, and the like. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed. The processing unit 701 may be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, and an NPU.

In particular, according to embodiments of the present disclosure, the methods described above with reference to the accompanying drawings may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a readable medium thereof, the computer program containing program code for performing the methods of the accompanying drawings. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 709 and/or installed from the removable medium 711 .

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 disclosure. In this regard, each block in the diagram or block diagram may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function. executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks 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 is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The units or modules involved in the embodiments of the present disclosure can be implemented in software or hardware. The described units or modules may also be provided in the processor, and the names of these units or modules do not constitute a limitation on the units or modules themselves in certain circumstances.

As another aspect, the present disclosure also provides a computer-readable storage medium, and the computer-readable storage medium may be a computer-readable storage medium included in the nodes described in the foregoing embodiments; A computer-readable storage medium that fits into a device. The computer-readable storage medium stores one or more programs used by one or more processors to perform the methods described in the present disclosure.

The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. It should be understood by those skilled in the art that the scope of the invention involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover the above technical features without departing from the inventive concept. Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above features with the technical features disclosed in the present disclosure (but not limited to) with similar functions.

Claims

A map construction method, including:

A node division step, wherein the first area is divided into nodes;

a node state and position acquisition step, wherein the state and position of the node are acquired;

A semantic label acquiring step, wherein a semantic label is acquired according to the node in the first area;

The step of obtaining the semantic label state, wherein the first state and/or the second state of the semantic label is obtained,

The first area is an area in a specific area that can be occupied by a mobile device.
The method according to claim 1, wherein the step of dividing the nodes comprises:

The first area is divided into the nodes according to the area perceived by the mobile device and/or the area occupied by the mobile device.
The method of claim 1, wherein:

obtaining the location of the node using a simultaneous localization and mapping method; and/or

The state of the node is obtained using a visual method.
The method according to claim 1, wherein the state of the node comprises:

Occupied state, not occupied state.
The method according to claim 4, wherein the step of acquiring the semantic label comprises:

The semantic labels are obtained using a clustering method according to the states and positions of the nodes in the first region.
The method according to claim 1, wherein the first state of the semantic label comprises:

unblocked state, crowded state, jammed state; and/or

The second state of the semantic tag includes:

Locked state, unlocked state.
The method of claim 6, wherein:

Under the condition that the continuous nodes connecting both sides of the semantic label in the semantic label are in the occupied state, the first state of the semantic label is the blocked state;

Under the condition that the number of the nodes in the occupied state in the semantic label is greater than a first threshold, or the proportion of the nodes in the occupied state in the semantic label is greater than a second threshold, the semantic The first state of the tag is the congestion state.
The method of claim 6, wherein:

Under the condition that the first state of the semantic label is the unblocked state, or the first state of the semantic label is the crowded state and the congestion index is less than or equal to the third threshold, the second state of the semantic label is the unlocked state ;

The second state of the semantic label is locked when the first state of the semantic label is a congestion state, or the first state of the semantic label is a crowded state and the congestion index is greater than the third threshold state.
A method for navigating a mobile device according to the map construction method according to any one of claims 1-8, comprising:

a navigation start and end position obtaining step, wherein the navigation start position and the navigation end position of the mobile device are obtained;

Navigation path planning step, wherein based on the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node are calculated navigation path;

a moving step, wherein the mobile device is controlled to move along the navigation path;

A state update step, wherein the state of the node, the first state of the semantic label and/or the second state of the semantic label are updated according to the location of the mobile device and/or the detection result of the mobile device ;

A navigation path update step, wherein the navigation path is updated according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node .
The method according to claim 9, wherein the navigation path planning step comprises:

Under the condition that the navigation start position and the navigation end position are within the same semantic label, the navigation path is calculated using a topology-graph level path planning algorithm;

Under the condition that the navigation start position and the navigation end position are not within the same semantic label, the navigation path is calculated using a semantic label-level path planning algorithm.
A map construction device, comprising:

a node division module, configured to divide the first area into nodes;

a node state and location acquisition module, configured to acquire the state and location of the node;

a semantic label obtaining module, configured to obtain a semantic label according to the node in the first area;

a semantic tag state acquisition module, configured to acquire the first state and/or the second state of the semantic tag,

The first area is an area in a specific area that can be occupied by a mobile device.
The apparatus according to claim 11, wherein the node division module is further configured to:

According to the area perceived by the mobile device and/or the area occupied by the mobile device, an area that may be occupied by the mobile device in the first area is divided into the nodes.
The apparatus of claim 11, wherein:

obtaining the location of the node using a simultaneous localization and mapping method; and/or

The state of the node is obtained using a visual method.
The apparatus according to claim 11, wherein the state of the node comprises:

Occupied state, not occupied state.
The apparatus according to claim 14, wherein the semantic label acquisition module is further configured to:

The semantic labels are obtained using a clustering method according to the states and positions of the nodes in the first region.
The apparatus according to claim 11, wherein the first state of the semantic label comprises:

unblocked state, crowded state, jammed state; and/or

The second state of the semantic tag includes:

Locked state, unlocked state.
The apparatus of claim 16, wherein:

Under the condition that the continuous nodes connecting both sides of the semantic label in the semantic label are in the occupied state, the first state of the semantic label is the blocked state;

Under the condition that the number of the nodes in the occupied state in the semantic label is greater than a first threshold, or the proportion of the nodes in the occupied state in the semantic label is greater than a second threshold, the semantic The first state of the tag is the congestion state.
The apparatus of claim 16, wherein:

Under the condition that the first state of the semantic label is the unblocked state, or the first state of the semantic label is the crowded state and the congestion index is less than or equal to the third threshold, the second state of the semantic label is the unlocked state ;

The second state of the semantic label is locked when the first state of the semantic label is a congestion state, or the first state of the semantic label is a crowded state and the congestion index is greater than the third threshold state.
A mobile device navigation device of the map construction device according to any one of claims 11-18, comprising:

a navigation start and end position acquisition module, configured to acquire a navigation start position and a navigation end position of the mobile device;

A navigation path planning module configured to base on the navigation start position, the navigation end position, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node Calculate the navigation path;

a movement module configured to control the mobile device to move along the navigation path;

A state update module, configured to update the state of the node, the first state of the semantic label and/or the second state of the semantic label according to the location of the mobile device and/or the detection result of the mobile device state;

A navigation path update module configured to update the navigation according to the updated state of the node, the first state of the semantic label and/or the second state of the semantic label, and the state and position of the node path.
The apparatus according to claim 19, wherein the navigation path planning module is further configured to:

Under the condition that the navigation start position and the navigation end position are within the same semantic label, the navigation path is calculated using a topology-graph level path planning algorithm;

Under the condition that the navigation start position and the navigation end position are not within the same semantic label, the navigation path is calculated using a semantic label-level path planning algorithm.
An electronic device, characterized by comprising a memory and a processor; wherein,

The memory is for storing one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method of any of claims 1-10.
A readable storage medium on which computer instructions are stored, characterized in that, when the computer instructions are executed by a processor, the method according to any one of claims 1-10 is implemented.