Science popularization robot control method and system

Abstract

The invention discloses a science popularization robot control method and system, and is applied to a robot intelligent control technology, and the method comprises the steps: obtaining a planar graph of a science popularization venue, and constructing a circulation region and an exhibition stand region; translating the exhibition stand area towards the boundary of the circulation area to the circulation area to form a driving area; an undirected graph is constructed according to the position relation of the multiple different driving areas, and a global path of the science popularization robot driving in the science popularization venue is constructed according to the undirected graph; and when the science popularization robot is in the cruise mode, the science popularization robot travels along the global path. According to the method, the planar graph of the science popularization venue can be quickly converted into the undirected graph capable of carrying out subsequent path operation, a calculation basis is provided for calculation of a cruising route of the science popularization robot in a daily state, and a calculation basis is also provided for a navigation route possibly needed by the science popularization robot; meanwhile, the method can be applied to various different science and technology venues for route planning, and has very high applicability.

Description

Technical Field

[0001] The present invention relates to the technical field of robot intelligent control, and particularly relates to a control method and system for a science popularization robot. Background Art

[0002] In the science popularization venue of traditional Chinese medicine culture, the science popularization robot can introduce in detail the development history of traditional Chinese medicine, famous doctors in past dynasties, classic works of traditional Chinese medicine, the efficacy and usage taboos of various Chinese medicinal materials, the composition and application of traditional Chinese medicine prescriptions, etc. in multiple sessions, effectively improving the efficiency of science popularization work and promoting the digitalization of science popularization construction.

[0003] Since the science popularization venue of traditional Chinese medicine culture undertakes the science popularization work for different groups in a region, the personnel are relatively dense in the daily environment, which poses a challenge to the safe operation of the science popularization robot operating in the venue; especially in a relatively narrow venue, collisions between the science popularization robot and visitors are likely to occur. In the prior art, the science popularization robot mostly relies on methods such as radar and collision detection to avoid personnel, and its specific operation route lacks effective planning, increasing the collision risk. Summary of the Invention

[0004] In order to at least overcome the above deficiencies in the prior art, the purpose of the present application is to provide a control method and system for a science popularization robot.

[0005] In a first aspect, the present application provides a control method for a science popularization robot, including: Obtain the floor plan of the science popularization venue, and construct a circulation area and a plurality of different exhibition stand areas according to the floor plan; Translate the boundary of the exhibition stand area facing the circulation area into the circulation area by a preset distance, and use the area generated by the translation as the driving area of the science popularization robot; Construct an undirected graph according to the positional relationship of a plurality of different driving areas, and construct a global path for the science popularization robot to drive in the science popularization venue according to the undirected graph; When the science popularization robot is in the cruise mode, the science popularization robot drives along the global path.

[0006] In a possible implementation manner, constructing an undirected graph according to the positional relationship of a plurality of different driving areas includes: Obtain the boundary after translation of each exhibition stand area as the central axis for the science popularization robot to drive; When the central axis is an open line, search for the endpoint of the other central axis that is closest to the endpoint of this central axis; if the searched central axis and this central axis intersect, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct a connection line between the two closest endpoints as a new path; When the central axis is a closed line, search for the endpoints of at least two other central axes that are closest to this central axis; if the searched central axis intersects with this central axis, use the intersection point as a driving node; if the searched central axis and this central axis do not intersect, construct the shortest connection line from the closest endpoint found to this central axis as a new added path; When the new added path is not in the circulation area or the closest distance between the new added path and the obstacle is less than half of the preset distance, translate the new added path towards the circulation area until the closest distance between the new added path and the obstacle is greater than or equal to half of the preset distance, and merge the translated path and the movement path of the endpoints of the new added path during the translation process to form a new added path that replaces the original new added path; Use the endpoints of the new added path as driving nodes, and use the new added path or the central axis between adjacent driving nodes as driving paths; Construct an initial undirected graph with the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as the weights of the edges; Add new nodes at the midpoints of the edges corresponding to the central axes in the initial undirected graph, and update the weights of all edges to form the undirected graph.

[0007] In a possible implementation manner, the generation of the global path includes: Select one of the new nodes at the outermost end of the science popularization venue as the initial node, and find the shortest path passing through all the new nodes in the undirected graph as the global path.

[0008] In a possible implementation manner, it further includes: When the science popularization robot receives a voice signal through the voice receiving device, identify the voice signal to generate voice recognition data; If the voice recognition data contains a first keyword, the science popularization robot enters the navigation mode; In the navigation mode, the science popularization robot identifies the destination in the voice recognition data and sends it to the cloud server, receives the navigation path generated by the cloud server according to the undirected graph, the destination, and the current position of the science popularization robot, and drives along the navigation route to the destination; If the voice recognition data contains a second keyword, the science popularization robot enters the explanation mode; In the explanation mode, the science popularization robot identifies the explanation prompt words in the voice recognition data and sends them to the cloud server, receives the explanation information feedback by the cloud server according to the explanation prompt words, and performs voice broadcast according to the explanation information.

[0009] In a possible implementation, the generation of the navigation route includes: The popular science robot identifies the destination from the speech recognition data according to the first keyword, and sends the destination and the current position of the popular science robot to the cloud server; The cloud server generates a temporary node corresponding to the current position in the undirected graph, updates the weights of the edges adjacent to the temporary node to form a temporary undirected graph, uses the temporary node as the starting node, and uses the node corresponding to the destination as the end node; The cloud server finds the shortest path from the starting node to the end node in the undirected graph as the navigation path.

[0010] In a possible implementation, the cloud server is configured with a localized question-and-answer large model and a knowledge base corresponding to the popular science venue; When the cloud server receives the explanation prompt word, it sends the explanation prompt word to the question-and-answer large model with the knowledge base and receives the answer information given by the question-and-answer large model; The cloud server sends the answer information as the explanation information to the popular science robot, and the popular science robot broadcasts the explanation information by voice.

[0011] In a second aspect, the present application further provides a popular science robot control system, including a cloud server and a popular science robot; The cloud server is configured to: Obtain the floor plan of the popular science venue, and construct a circulation area and a plurality of different exhibition booth areas according to the floor plan; Translate the boundary of the exhibition booth area facing the circulation area towards the circulation area by a preset distance, and use the area generated by the translation as the driving area of the popular science robot; Construct an undirected graph according to the positional relationship of a plurality of different driving areas, and construct a global path for the popular science robot to drive in the popular science venue according to the undirected graph; The popular science robot is configured to: When the popular science robot is in the cruise mode, it drives along the global path.

[0012] In a possible implementation, the cloud server is further configured to: Obtain the boundary of each exhibition booth area after translation as the central axis for the popular science robot to drive; When the central axis is an open line, search for the endpoints of other central axes that are closest to the endpoints of this central axis; if the searched central axis intersects with this central axis, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct a connection line between the two closest endpoints as the new added path; When the central axis is a closed line, search for at least two endpoints of other central axes that are closest to this central axis; if the searched central axis intersects with this central axis, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct the shortest connection line from the closest endpoints found to this central axis as the new added path; When the new added path is not in the circulation area or the closest distance between the new added path and the obstacle is less than half of the preset distance, translate the new added path towards the circulation area until the closest distance between the new added path and the obstacle is greater than or equal to half of the preset distance, and merge the translated path and the movement path of the endpoints of the new added path during the translation process to form a new new added path that replaces the original new added path; Use the endpoints of the new added path as driving nodes, and use the new added path or the central axis between adjacent driving nodes as the driving path; With the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as the weights of the edges, construct an initial undirected graph; Add new nodes at the midpoints of the edges corresponding to the central axes in the initial undirected graph, and update the weights of all edges to form the undirected graph.

[0013] In a possible implementation, the cloud server is further configured to: Select one of the new nodes at the outermost part of the science popularization venue as the initial node, and find the shortest path passing through all the new nodes in the undirected graph as the global path.

[0014] In a possible implementation, the science popularization robot is further configured to: When a voice signal is received through the voice receiving device, identify the voice signal to generate voice recognition data; If the voice recognition data contains the first keyword, enter the navigation mode; In the navigation mode, identify the destination in the voice recognition data and send it to the cloud server, receive the navigation path generated by the cloud server according to the undirected graph, the destination, and the current position of the science popularization robot, and drive along the navigation route to the destination; If the voice recognition data contains the second keyword, enter the explanation mode; In the explanation mode, the explanation prompt words in the speech recognition data are identified and sent to the cloud server, and the explanation information fed back by the cloud server according to the explanation prompt words is received, and the explanation information is used for voice broadcast.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: By the above technical means, the present invention can quickly convert the floor plan of the science popularization venue into an undirected graph that can be used for subsequent path calculation, providing a calculation basis for the calculation of the cruising route of the science popularization robot in the daily state, and also providing a calculation basis for the navigation route that the science popularization robot may need; at the same time, the present application can be applied to a variety of different science and technology venues for route planning, and has strong applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not constitute a limitation to the embodiments of the present invention. In the drawings: Figure 1 It is a schematic diagram of the method steps of the embodiment of this application; Figure 2 It is the floor plan of the science popularization venue of the embodiment of this application; Figure 3 It is the floor plan of the science popularization venue after processing of the embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To make the objectives, technical solutions and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings in the embodiments of this application. It should be understood that the drawings in this application are only for the purpose of illustration and description, and are not used to limit the protection scope of this application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application show the operations implemented according to some embodiments of the embodiments of this application. It should be understood that the operations of the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of this application.

[0018] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application generally described and illustrated in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0019] Please refer to Figure 1 , which is a schematic flow chart of a popular science robot control method provided by an embodiment of the present invention. Further, the popular science robot control method may specifically include the content described in the following steps S1 - step S4.

[0020] S1: Obtain the floor plan of the popular science venue, and construct a circulation area and a plurality of different exhibition booth areas according to the floor plan; S2: Translate the exhibition booth area towards the boundary of the circulation area by a preset distance into the circulation area, and use the area generated by the translation as the driving area of the popular science robot; S3: Construct an undirected graph according to the positional relationship of a plurality of different driving areas, and construct a global path for the popular science robot to drive in the popular science venue according to the undirected graph; S4: When the popular science robot is in the cruise mode, the popular science robot drives along the global path.

[0021] When the embodiments of the present application are implemented, a technical solution that can quickly design the route of a popular science robot through calculation is provided. First, the floor plan of the popular science venue needs to be obtained, and the circulation area and the exhibition booth area need to be marked in the figure; the circulation area is the area where people and popular science robots can pass in the popular science venue, and the exhibition booth area is the area for displaying exhibits or other displays; in the embodiments of the present application, the exhibition booth area is divided into multiple ones according to different exhibit types. Generally, in a popular science venue, the exhibition booth areas are independent of each other, so generally there will be no overlapping situation in the exhibition booth areas; since the popular science robot in the present application has an explanation function, when designing the route of the popular science robot, it is necessary to let the popular science robot pass through each exhibition booth area to provide real-time interaction and explanation. At the same time, it is necessary to let the popular science robot invade the circulation area where people walk as little as possible; so in the embodiments of the present application, by constructing the driving area, an undirected graph corresponding to the venue is constructed for path calculation.

[0022] In the embodiments of the present application, the driving area mainly provides an area for people to stand in front of the exhibition booth and for the robot to drive. Therefore, the selection of the general preset distance needs to be determined according to the size of the science popularization robot. Generally, the preset distance needs to be equal to the distance where people stand plus half of the diameter of the science popularization robot. When the general standing distance of people is about 100 cm and the diameter of the science popularization robot is 80 cm, the preset distance can be selected as 150 cm. After constructing the driving area, points that the science popularization robot needs to pass through during driving in the driving area, such as the endpoints of the boundary, etc., can be used to generate an undirected graph. It should be understood that there may be gaps between different exhibition booths, so some new driving paths need to be generated to generate a more accurate undirected graph. After generating the undirected graph for all the points and paths that the science popularization robot needs to drive in the venue, some path optimization algorithms can be used to generate the global path. At the same time, this undirected graph can also provide an operation basis for route generation when the science popularization robot needs to run in the direction of a certain exhibition booth. In the embodiments of the present application, in the state without special instructions, the science popularization robot is in the cruise mode and runs in the venue according to the global path to facilitate providing services for customers. Through the above technical means, the present application can quickly convert the floor plan of the science popularization venue into an undirected graph that can be used for subsequent path operations, providing a calculation basis for calculating the cruise route of the science popularization robot in the daily state and also providing a calculation basis for the navigation route that the science popularization robot may need. At the same time, the present application can be applied to route planning in a variety of different science and technology venues, with strong applicability.

[0023] In a possible implementation manner, constructing an undirected graph according to the positional relationship of multiple different driving areas includes: Obtain the boundary after translation of each of the exhibition booth areas as the central axis for the science popularization robot to drive; When the central axis is an open line, search for the endpoints of other central axes that are closest to the endpoints of this central axis; if the searched central axis and this central axis intersect, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct a connection line between the two closest endpoints as a new path; When the central axis is a closed line, search for at least two endpoints of other central axes that are closest to this central axis; if the searched central axis and this central axis intersect, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct the shortest connection line from the searched closest endpoints to this central axis as a new path; When the newly added path is not in the circulation area or the closest distance between the newly added path and the obstacle is less than half of the preset distance, translate the newly added path towards the circulation area until the closest distance between the newly added path and the obstacle is greater than or equal to half of the preset distance, and merge the translated path and the movement path of the endpoints of the newly added path during the translation process to form a new newly added path that replaces the newly added path; Use the endpoints of the newly added path as driving nodes, and use the newly added path or the central axis between adjacent driving nodes as the driving path; Construct an initial undirected graph with the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as the weights of the edges; Add new nodes at the midpoints of the edges corresponding to the central axis in the initial undirected graph, and update the weights of all edges to form the undirected graph.

[0024] When implementing the embodiments of the present application, the inventors found that in general popular science venues, exhibition stands are mainly presented in two ways. One is the exhibition stand arranged by continuous walls or temporary supports, which only provides one exhibition direction; the other is the exhibition stand independently arranged in the middle of the venue, which provides all-round exhibition directions. Therefore, in the embodiments of the present application, these two situations are processed separately. In order to facilitate the computer to identify these two situations, a method of using the central axis for category discrimination is adopted; for the first type of exhibition stand, the central axis generated by it is generally an open line, that is, a line with two endpoints, while for the second type of exhibition stand, the central axis generated by it is generally a closed line, that is, there are no endpoints.

[0025] In the embodiments of the present application, based on the above classification process, the central axes generated by the two types of exhibition stands are processed separately; for the central axis generated by the first type of exhibition stand, it is necessary to first find the endpoints of other central axes that are closest to the endpoints of the central axis and try to connect with these endpoints. If an intersection has occurred, it means that there is a connection situation, and the intersection point is the connection point; if no intersection has occurred, a connection line is constructed to complete the connection; for the second type of exhibition stand, the central axes corresponding to these independently existing exhibition stands are preferentially connected to the central axis of the first type of exhibition stand. Therefore, it is necessary to find at least two endpoints that are closest to the central axis to form a richer route. It should be understood that for the second type of exhibition stand, there may be a continuous series of independent exhibition stands. At this time, when generating the driving area, these continuous independent exhibition stands need to be regarded as a whole for generating the driving area. The specific process is as follows: Fill the gaps between the continuous series of independent exhibition stands to form a pseudo-exhibition stand area; Merge the continuous series of independent exhibition stands and the pseudo-exhibition stand area to form an exhibition stand area; Construct a driving area with the newly formed exhibition stand area.

[0026] In the embodiments of the present application, the newly added path is a path newly generated during the process of connecting the driving areas. At this time, it is necessary to consider the safety of the popular science robot when driving on these paths; at this time, it is necessary to screen out the newly added paths that are not in the circulation area and the newly added paths that are too close to the obstacles (such as walls, other exhibition stands, etc.) in the floor plan, and further optimize these newly added paths. The optimization process is carried out by means of path translation. The judgment criterion during translation is to translate to a distance greater than or equal to half of the preset distance from the above-mentioned obstacles. The main reason is that for the area of the newly added path, there is generally no exhibition stand, and the visiting crowd generally does not stay in this area. Therefore, appropriately relaxing the range can effectively reduce the intrusion of the popular science robot into the circulation area during operation.

[0027] After the construction of the central axis and the newly added paths is completed, select the intersection points of the endpoints of the newly added paths and the central axis as the driving nodes, and an initial undirected graph can be constructed. In the initial undirected graph, in order to express the positions of different exhibition stands, it is necessary to select the midpoints of the edges of the central axis to represent the specific exhibition stands; at this time, for an independent exhibition stand, since its closed central axis will be segmented and cut by the endpoints of the newly added paths, there may be multiple newly added nodes corresponding to the same exhibition stand. At this time, these nodes can all be retained, or at least one can be retained as appropriate. After adding the new nodes, the edges of the initial undirected graph will be further segmented, so it is necessary to further assign weights to the edges to finally form an undirected graph. This undirected graph covers all types of exhibition stands and possible passing paths, and can completely express the entire state of a popular science venue, which is very beneficial to the subsequent generation of optimized paths.

[0028] For example, please refer to Figure 2 , which shows a floor plan of a traditional Chinese medicine culture venue. The rightmost part is the practical operation area, which does not require the popular science robot to pass through. Therefore, it is removed and the driving area is generated. Please refer to Figure 3 , which shows the floor plan after the driving area is generated. The shaded part is the driving area. As can be seen from Figure 3 , there are two independent exhibition stands. One is the circular exhibition stand on the left, and the driving area formed by it is circular. The other is the independent exhibition stand formed by the merger of several small independent exhibition stands on the right, and the driving area formed by it is square-shaped; at this time, it is necessary to generate newly added paths, which are represented by dotted lines in Figure 3 . It can be seen that some newly added paths are blocked. At this time, these newly added paths need to be extended to the circulation area to form new newly added paths; when all paths are generated, it is necessary to select nodes, which are represented by small circles in Figure 3 . An undirected graph can be generated according to the connection relationship and connection length of these small circles.

[0029] In a possible implementation, the generation of the global path includes: Select an added node at the outermost end of the popular science venue as the initial node, and find the shortest path passing through all the added nodes in the undirected graph as the global path.

[0030] When implementing the embodiments of the present application, to form a global path, it is necessary to first select an added node at the outermost end of the popular science venue as the starting point. Generally, the added node at the outermost end is the added node closest to the entrance or exit of the popular science venue. The main reason is that when calculating the global path through Dijkstra's algorithm, selecting the outermost node can reduce the number of optional paths at the beginning of generating the global path, thereby accelerating the algorithm calculation. Specifically, when calculating the global path through Dijkstra's algorithm, a first set and a second set are generated; during the initialization of the algorithm, the initial node is added to the first set, and the remaining added nodes are added to the second set; the new node with the shortest edge distance from the second set to the initial node is found as the intermediate node and added to the first set, and the path from the initial node to this intermediate node is formed as the initial path; the new node with the shortest edge distance from the second set to this intermediate node is found as the new intermediate node and added to the first set, and the path between this intermediate node and the new intermediate node is formed as the intermediate path; the above path finding process is repeated until the second set becomes an empty set, and the initial path and all the intermediate paths are spliced to form the global path.

[0031] In a possible implementation, it further includes: When the popular science robot receives a voice signal through the voice receiving device, the voice signal is recognized to generate voice recognition data; If the voice recognition data contains a first keyword, the popular science robot enters the navigation mode; In the navigation mode, the popular science robot identifies the destination in the voice recognition data and sends it to the cloud server, receives the navigation path generated by the cloud server according to the undirected graph, the destination and the current position of the popular science robot, and travels along the navigation route to the destination; If the voice recognition data contains a second keyword, the popular science robot enters the explanation mode; In the explanation mode, the popular science robot identifies the explanation prompt word in the voice recognition data and sends it to the cloud server, receives the explanation information fed back by the cloud server according to the explanation prompt word, and performs voice broadcast according to the explanation information.

[0032] When the embodiment of this application is implemented, the popular science robot also has a simple voice recognition system built in. Specifically, when implemented, the voice receiving device can use a Bluetooth microphone, and the voice broadcast can use Bluetooth headphones. When a voice signal comes from the Bluetooth microphone, the voice recognition process is activated. For the navigation mode, the corresponding first keywords can include: "I want to go", "How to go", "Where is it", etc. When entering the navigation mode, the destination of the voice recognition data can be found according to the type of the keyword. For example, the word closest to the first keyword is used as the destination. The popular science robot can upload data to the cloud server through the wifi network covering the popular science venue, and the cloud server generates a navigation path according to the undirected graph. Since there is no need to accurately identify the part of speech and the meaning of words, the computing power required by this popular science robot is extremely low, which can effectively reduce the robot usage cost of large-scale venues that require a large number of popular science robots.

[0033] In the embodiment of this application, the popular science robot also needs to identify the second keyword and enter the explanation mode. The second keyword can include words such as "I want to listen", "What is it", "Tell me", etc. Similarly, in the embodiment of this application, the popular science robot only needs to find the prompt word according to the second keyword and send it to the cloud server, and the cloud server can complete the generation of the explanation words.

[0034] In a possible implementation manner, the generation of the navigation route includes: The popular science robot identifies the destination from the voice recognition data according to the first keyword, and sends the destination and the current position of the popular science robot to the cloud server; The cloud server generates a temporary node corresponding to the current position in the undirected graph, updates the weights of the edges adjacent to the temporary node to form a temporary undirected graph, uses the temporary node as the starting node, and uses the node corresponding to the destination as the end node; The cloud server finds the shortest path from the starting node to the end node in the undirected graph as the navigation path.

[0035] When the embodiment of this application is implemented, during the generation process of the navigation path, it is necessary to correct the undirected graph to generate a temporarily used temporary undirected graph. The temporary undirected graph adds a temporary node, and the weights of the two edges adjacent to the temporary node are also updated. It should be understood that for the undirected graph of navigation, the weight of the edge is the length of the edge. The shortest path can be found through the corresponding pathfinding algorithm to form the navigation path.

[0036] In a possible implementation manner, the cloud server is configured with a localized question-and-answer large model and a knowledge base corresponding to the popular science venue; When the cloud server receives the explanation prompt word, it sends the explanation prompt word to the question-and-answer large model with the knowledge base and receives the answer information given by the question-and-answer large model; The cloud server sends the answer information as the explanation information to the popular science robot, and the popular science robot broadcasts the explanation information by voice.

[0037] When implementing the embodiments of the present application, an intelligent explanation is realized by using a large model based on local deployment. Among them, it is necessary to build a knowledge base for the question-and-answer large model. The knowledge base needs to include the exhibit information of all exhibition stands in the popular science venue and corresponding extended information. When the question-and-answer large model receives the explanation prompt word, it will generate corresponding answer information as the explanation words according to the information in the knowledge base. This answer information will be broadcast by the popular science robot to achieve intelligent explanation. This method also has very low requirements for the computing power of the popular science robot itself. Most of the computing processes are realized by the cloud server, which is very conducive to the large-scale deployment of popular science robots. At the same time, by adding languages to the explanation prompt words, multi-language broadcasting can be realized without the help of other software.

[0038] Based on the same inventive concept, the present application also provides a control system for a popular science robot, including a cloud server and a popular science robot; The cloud server is configured to: Obtain the floor plan of the popular science venue and construct a circulation area and multiple different exhibition stand areas according to the floor plan; Translate the boundary of the exhibition stand area facing the circulation area towards the circulation area by a preset distance, and use the area generated by the translation as the driving area of the popular science robot; Construct an undirected graph according to the positional relationship of multiple different driving areas, and construct a global path for the popular science robot to drive in the popular science venue according to the undirected graph; The popular science robot is configured to: When the popular science robot is in the cruise mode, it drives along the global path.

[0039] In a possible implementation manner, the cloud server is further configured to: Obtain the boundary after translation of each exhibition stand area as the central axis for the popular science robot to drive; When the central axis is an open line, search for the endpoint of the other central axis that is closest to the endpoint of this central axis; if the searched central axis and this central axis intersect, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct a connection line between the two closest endpoints as the new path; When the central axis is a closed line, search for the endpoints of at least two other central axes that are closest to this central axis; if the searched central axis intersects with this central axis, use the intersection point as the driving node; if the searched central axis and this central axis do not intersect, construct the shortest connection line from the closest endpoint found to this central axis as the new added path; When the new added path is not in the circulation area or the closest distance between the new added path and the obstacle is less than half of the preset distance, translate the new added path towards the circulation area until the closest distance between the new added path and the obstacle is greater than or equal to half of the preset distance, and merge the translated path and the movement path of the endpoints of the new added path during the translation process to form a new new added path that replaces the original new added path; Use the endpoints of the new added path as driving nodes, and use the new added path or the central axis between adjacent driving nodes as the driving path; Construct an initial undirected graph with the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as the weights of the edges; Add new nodes at the midpoints of the edges corresponding to the central axis in the initial undirected graph, and update the weights of all edges to form the undirected graph.

[0040] In a possible implementation manner, the cloud server is further configured to: Select one of the new nodes at the outermost end of the science popularization venue as the initial node, and find the shortest path passing through all the new nodes in the undirected graph as the global path.

[0041] In a possible implementation manner, the science popularization robot is further configured to: When a voice signal is received through the voice receiving device, identify the voice signal to generate voice recognition data; If the voice recognition data contains the first keyword, enter the navigation mode; In the navigation mode, identify the destination in the voice recognition data and send it to the cloud server, receive the navigation path generated by the cloud server according to the undirected graph, the destination, and the current position of the science popularization robot, and drive along the navigation route to the destination; If the voice recognition data contains the second keyword, enter the explanation mode; In the explanation mode, identify the explanation prompt words in the voice recognition data and send them to the cloud server, receive the explanation information feedback by the cloud server according to the explanation prompt words, and perform voice broadcast according to the explanation information.

[0042] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0043] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices or units, and can also be electrical, mechanical or other forms of connection.

[0044] The units described as separate components may or may not be physically separated. Obviously, those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0045] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0046] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a grid device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0047] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling a popular science robot, characterized in that: include: Obtaining a floor plan of the science and technology venue, and constructing a circulation area and a plurality of different exhibition booth areas according to the floor plan; The exhibition stand area is translated toward the boundary of the circulation area by a preset distance, and the area generated by the translation is used as the driving area of ​​the popular science robot; Constructing an undirected graph according to the positional relationship of a plurality of different driving areas, and constructing a global path for the popular science robot to drive in the popular science venue according to the undirected graph; When the science popularization robot is in the cruise mode, the science popularization robot travels along the global path.

2. A popular science robot control method according to claim 1, characterized in that: Constructing an undirected graph based on the positional relationship of multiple different driving areas includes: Obtaining the boundary of each booth area after translation as the central axis of the popular science robot; When the central axis is an open line, search for the endpoint of another central axis closest to the endpoint of the central axis; if the searched central axis intersects with the central axis, the intersection point is used as a travel node; if the searched central axis does not intersect with the central axis, a line connecting the two closest endpoints is constructed as a newly added path; When the central axis is a closed line, search for the endpoints of at least two other central axes closest to the central axis; if the searched central axis intersects with the central axis, use the intersection point as a travel node; if the searched central axis does not intersect with the central axis, construct the shortest connection from the searched closest endpoint to the central axis as a newly added path; When the newly added path is not in the circulation area or the closest distance between the newly added path and the obstacle is less than half of the preset distance, the newly added path is translated toward the circulation area until the closest distance between the newly added path and the obstacle is greater than or equal to half of the preset distance, and the translated path and the motion path of the endpoint of the newly added path during the translation process are merged to form a new newly added path that replaces the newly added path; The endpoints of the newly added paths are used as driving nodes, and the newly added paths or central axes between adjacent driving nodes are used as driving paths; Constructing an initial undirected graph with the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as edge weights; In the initial undirected graph, a new node is added to the midpoint of the edge corresponding to the central axis, and the weights of all edges are updated to form the undirected graph.

3. A popular science robot control method according to claim 2, characterized in that: The generation of the global path includes: A newly added node at the end of the popular science venue is selected as an initial node, and the shortest path passing through all the newly added nodes is searched in the undirected graph as the global path.

4. A popular science robot control method according to claim 2, characterized in that: Also includes: When the popular science robot receives a voice signal through a voice receiving device, the voice signal is recognized to generate voice recognition data; If the voice recognition data contains the first keyword, the popular science robot enters a navigation mode; In the navigation mode, the popular science robot recognizes the destination in the voice recognition data and sends it to the cloud server, receives the navigation path generated by the cloud server according to the undirected graph, the destination and the current position of the popular science robot, and drives to the destination along the navigation route; If the voice recognition data contains the second keyword, the popular science robot enters the explanation mode; In the explanation mode, the popular science robot recognizes the explanation prompt words in the voice recognition data and sends them to the cloud server, receives the explanation information fed back by the cloud server according to the explanation prompt words, and performs voice broadcast according to the explanation information.

5. A popular science robot control method according to claim 4, characterized in that: The generation of the navigation route includes: The popular science robot identifies a destination from the voice recognition data according to the first keyword, and sends the destination and the current location of the popular science robot to a cloud server; The cloud server generates a temporary node corresponding to the current position in the undirected graph, updates the weights of the edges adjacent to the temporary node to form a temporary undirected graph, and uses the temporary node as the starting node and the node corresponding to the destination as the end node; The cloud server searches the undirected graph for the shortest path from the start node to the end node as the navigation path.

6. A method for controlling a popular science robot according to claim 4, characterized in that: The cloud server is configured with a localized question-answering large model and a knowledge base corresponding to the science museum; When the cloud server receives the explanation prompt word, it sends the explanation prompt word to the question-answering large model having the knowledge base, and receives the answer information made by the question-answering large model; The cloud server sends the answer information as the explanation information to the science popularization robot, and the science popularization robot broadcasts the explanation information in voice.

7. A popular science robot control system, characterized in that: Including cloud servers and popular science robots; The cloud server is configured as follows: Obtaining a floor plan of the science and technology venue, and constructing a circulation area and a plurality of different exhibition booth areas according to the floor plan; The exhibition stand area is translated toward the boundary of the circulation area by a preset distance, and the area generated by the translation is used as the driving area of ​​the popular science robot; Constructing an undirected graph according to the positional relationship of a plurality of different driving areas, and constructing a global path for the popular science robot to drive in the popular science venue according to the undirected graph; The popular science robot is configured as follows: When the popular science robot is in the cruise mode, it travels along the global path.

8. A popular science robot control system according to claim 7, characterized in that: The cloud server is also configured as: Obtaining the boundary of each booth area after translation as the central axis of the popular science robot; When the central axis is an open line, search for the endpoint of another central axis closest to the endpoint of the central axis; if the searched central axis intersects with the central axis, the intersection point is used as a travel node; if the searched central axis does not intersect with the central axis, a line connecting the two closest endpoints is constructed as a newly added path; When the central axis is a closed line, search for the endpoints of at least two other central axes closest to the central axis; if the searched central axis intersects with the central axis, use the intersection point as a travel node; if the searched central axis does not intersect with the central axis, construct the shortest connection from the searched closest endpoint to the central axis as a newly added path; When the newly added path is not in the circulation area or the closest distance between the newly added path and the obstacle is less than half of the preset distance, the newly added path is translated toward the circulation area until the closest distance between the newly added path and the obstacle is greater than or equal to half of the preset distance, and the translated path and the motion path of the endpoint of the newly added path during the translation process are merged to form a new newly added path that replaces the newly added path; The endpoints of the newly added paths are used as driving nodes, and the newly added paths or central axes between adjacent driving nodes are used as driving paths; Constructing an initial undirected graph with the driving nodes as nodes, the driving paths as edges, and the lengths of the driving paths as edge weights; In the initial undirected graph, a new node is added to the midpoint of the edge corresponding to the central axis, and the weights of all edges are updated to form the undirected graph.

9. A popular science robot control system according to claim 8, characterized in that: The cloud server is also configured as: A newly added node at the end of the popular science venue is selected as an initial node, and the shortest path passing through all the newly added nodes is searched in the undirected graph as the global path.

10. The popular science robot control system according to claim 7, characterized in that: The popular science robot is also configured as: When a voice signal is received by a voice receiving device, the voice signal is recognized to generate voice recognition data; If the voice recognition data contains the first keyword, entering a navigation mode; In the navigation mode, the destination in the voice recognition data is identified and sent to the cloud server, a navigation path generated by the cloud server according to the undirected graph, the destination and the current position of the popular science robot is received, and the robot travels to the destination along the navigation route; If the voice recognition data contains a second keyword, entering an explanation mode; In the explanation mode, the explanation prompt words in the voice recognition data are identified and sent to the cloud server, the explanation information fed back by the cloud server according to the explanation prompt words is received, and voice broadcast is performed according to the explanation information.

Images