CN114770495A - Robot execution business operation method and device and robot - Google Patents
Robot execution business operation method and device and robot Download PDFInfo
- Publication number
- CN114770495A CN114770495A CN202210205081.3A CN202210205081A CN114770495A CN 114770495 A CN114770495 A CN 114770495A CN 202210205081 A CN202210205081 A CN 202210205081A CN 114770495 A CN114770495 A CN 114770495A
- Authority
- CN
- China
- Prior art keywords
- robot
- information
- map
- position information
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000008569 process Effects 0.000 claims abstract description 41
- 238000013135 deep learning Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000005507 spraying Methods 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000010223 real-time analysis Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241001122767 Theaceae Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1661—Programme controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method and a device for a robot to execute business operation and the robot. The method comprises the following steps: in the process of robot navigation, map information established based on a world coordinate system is dynamically updated; acquiring current position and attitude data of the robot, and acquiring current position information of the robot in a world coordinate system according to the position and attitude data; and judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information. By adopting the technical scheme, the safety of the robot in the autonomous navigation process can be improved, and the robot can execute various working tasks more simply, conveniently and feasibly.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method and a device for a robot to execute business operation and the robot.
Background
With the rapid development of sensor technology, artificial intelligence theory and computer technology, the field of robots is continuously and deeply studied, and various autonomous mobile robots with environment perception capability, behavior control and dynamic decision-making capability and man-machine interaction capability are developed. Compared with the traditional industrial robot, the autonomous mobile robot has the greatest characteristic of freely moving in a complex environment and completing various work tasks.
In the related art, in order to realize autonomous navigation of a robot according to a preset route in a complex environment, a laser mapping mode is generally adopted, required map construction is performed by correcting a laser map, and subsequent navigation positioning work is performed according to the map established by laser, however, the laser mapping precision cannot meet higher requirements, laser navigation belongs to two-dimensional obstacle avoidance, the effect is poor, most laser sensors are deployed at the top end, the height of a machine body is increased, and meanwhile, a detection blind area may exist in a short obstacle, so that the robot may fall, rollover, collision and other problems in the complex environment.
Furthermore, to accomplish the various tasks that a robot performs during autonomous movement, software programming is typically employed, and such programming typically involves extensive encoding to predict or attempt to predict each situation that the robot may encounter. This approach is not only costly from a time, effort and computer resource perspective, but also limits the capabilities of the robot.
Therefore, a robot navigation technical scheme is still lacked at present for the problem that the robot can execute various work tasks more conveniently and feasibly on the premise of ensuring the safety of the robot in the autonomous navigation process.
Disclosure of Invention
The invention mainly aims to disclose a method and a device for executing business operation by a robot and the robot, which at least solve the problems that the robot can execute various work tasks more simply and feasibly on the premise of ensuring the safety of the robot in the autonomous navigation process in the related technology, and a robot navigation technical scheme is lacked at present.
According to one aspect of the invention, a method for a robot to perform business operations is provided.
The method for the robot to execute the business operation comprises the following steps: in the process of robot navigation, map information established based on a world coordinate system is dynamically updated; acquiring current pose data of the robot, and acquiring current position information of the robot in a world coordinate system according to the pose data; and judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information.
According to another aspect of the present invention, there is provided a robot performing business operations apparatus.
The robot executing business operation device according to the invention comprises: the map updating module is used for dynamically updating map information established based on a world coordinate system when the robot carries out navigation; the acquisition module is used for acquiring the current position and attitude data of the robot and acquiring the current position information of the robot in a world coordinate system according to the position and attitude data; and the execution module is used for judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, and if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information.
According to yet another aspect of the present invention, a robot is provided.
The robot according to the present invention comprises: the memory is used for storing computer execution instructions; the processor is configured to execute the computer-executable instructions stored in the memory, so that the robot executes any one of the methods.
According to the invention, in the process of navigating the robot according to the path to be tracked, the map information established based on the world coordinate system is dynamically updated, a map with higher precision is established through real-time analysis and optimization, and the robot can be prevented from running to a dangerous area by combining the high-precision map and the positioning function of the robot, so that the safety of the robot is improved. Moreover, as the path to be tracked is bound in the map information, one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operations (such as rotation, arm action, water spraying, dust absorption, detour, corresponding equipment opening and the like), when the robot moves to the position where the business operations are bound, the business operations corresponding to the position can be executed, so that various work tasks can be completed more intelligently in the autonomous navigation process.
Drawings
FIG. 1 is a flow diagram of a method of a robot performing a business operation in accordance with an embodiment of the present invention;
fig. 2 is a block diagram of a robot performing a service operation apparatus according to an embodiment of the present invention;
fig. 3 is a block diagram of a robot according to an embodiment of the present invention.
Detailed Description
The following detailed description of specific embodiments of the present invention is provided in conjunction with the accompanying drawings.
According to the embodiment of the invention, a method for executing business operation by a robot is provided.
Fig. 1 is a flowchart of a method for a robot to perform a business operation according to an embodiment of the present invention. As shown in fig. 1, the method for the robot to perform the business operation includes:
step S101: in the process of robot navigation, map information established based on a world coordinate system is dynamically updated;
step S103: acquiring current pose data of the robot, and acquiring current position information of the robot in a world coordinate system according to the pose data;
step S105: and judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information.
By adopting the method shown in fig. 1, in the process of navigating the robot according to the path to be tracked, map information (such as a three-dimensional point cloud map and/or a semantic map) established based on a world coordinate system is dynamically updated, a higher-precision map is established through real-time analysis and optimization, and the robot can be prevented from running to a dangerous area by combining the high-precision map and the positioning function of the robot, so that the safety of the robot is improved. Moreover, as the path to be tracked is bound in the three-dimensional point cloud map and/or the semantic map, one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operations (such as rotation, arm action, water spraying, dust absorption, detour, corresponding equipment opening and the like), when the robot moves to the position where the business operations are bound, the business operations corresponding to the position can be executed, and thus, various work tasks are completed more intelligently in the autonomous navigation process.
The map information (e.g., a three-dimensional point cloud map and/or a semantic map) is established based on a world coordinate system, and the position coordinates of point cloud data points in the three-dimensional point cloud map in the world coordinate system or the position coordinates of various objects (e.g., tables, vases, elevators, etc.) in the semantic map in the world coordinate system can be determined.
Preferably, before the robot navigating, the method may further include: establishing a world coordinate system, and constructing a world map based on the world coordinate system; based on a plurality of sensor data, combining super-point cloud (super-point) information extracted by a deep learning algorithm, establishing a shallow semantic map, and binding the shallow semantic map and the world map.
The super-point cloud (super-point) information is point cloud information extracted by a deep learning algorithm, has stronger description capacity, and can assist a user or a robot in better positioning and mapping.
Preferably, before the robot navigation, the method may further include: establishing a world coordinate system, and constructing a world map based on the world coordinate system; establishing a deep semantic map based on semantic information extracted by a deep learning algorithm, and binding the deep semantic map with the world map, wherein the deep semantic map comprises: boundary information, category information.
In the preferred implementation process, through the initial pose and the specific operation scene condition of the robot, firstly establishing a world coordinate system of the robot, and constructing a world map based on the world coordinate system; then, a scene is described through received sensor data, such as image data, inertial sensor (IMU) data, odometer data, laser data and the like, and received super point cloud (super point cloud) information (point cloud data including higher dimensional information) extracted by a deep learning algorithm, a shallow semantic map is established, and then the shallow semantic map is bound with the world map, so that the map construction can be assisted and completed and the positioning accuracy can be improved by taking feature information of the deep learning map as shallow semantic information, and assisted positioning and map construction can be performed through the shallow semantic map.
In the preferred implementation process, a deep semantic map can be obtained based on semantic information extracted by a deep learning algorithm, and the feature information based on the deep learning map is used as shallow semantic information to assist in perfecting map construction and improving positioning accuracy; and binding a deep semantic map with the world map constructed based on the world coordinate system, wherein the deep semantic map comprises super point cloud information (point cloud information with descriptive capability) extracted by deep learning, in addition to basic visual point cloud information, and deep semantic information (the information can comprise boundary information of boundary point cloud information and deep semantic map, the cloud information is clustered to form point cloud cluster sets, and the mass center point of each point cloud cluster set is determined, for example, a k-means clustering algorithm is adopted, the similar relation of point cloud data points is judged by calculating the distance between different point cloud data points, the similar point cloud data points are put into the same category, specifically, firstly, a k value is required to be selected, the k is a preset clustering number, then initial k clustering points (namely mass center points) are required to be selected randomly, all points in the point cloud data set are then calculated as being the distance from the selected centroid point and classified as being closest to their centroid. After completion, the mean value of each cluster set needs to be calculated, and the point is used as a new centroid. The above steps are repeated repeatedly until the centroid is unchanged or slightly changed, and the final result is obtained.
Therefore, the local point cloud map is established into higher-dimensional centroid points with more description capacity based on deep semantic information, the method combines the semantic information with the traditional point cloud in a cluster fitting mode, the cluster points are used as the central points (centroid points) of the point cloud cluster which locally accords with the standard, directional extraction of local point cloud is carried out according to the boundary information, division of local extraction range is carried out according to the boundary information of the depth semantic map, the extracted point clouds are fitted into a high-dimensionality point cloud cluster set (which can be called road sign information) in a clustering mode, meanwhile, the relative relationship between different high-dimensional road sign information is established according to the existing high-dimensional road sign information, in the actual running process of the robot, the optimization and correction of the track and the positioning are carried out by observing one or more same road signs, so that the whole positioning precision and the map precision are improved.
Obtaining semantic information of current deep learning, judging related semantic information (including object type information such as an elevator, a plant, a vase and the like) identified by the current deep learning in a time alignment mode, and converting the related semantic information into a world coordinate system through a relative pose. It should be noted that if the part of data overlaps with the previously constructed deep semantic map, the part of data supplements the high-dimensional point cloud cluster clustered in the deep semantic map (for example, if the deep semantic map is an item 1 point cloud cluster of length x, width y, and height z, and the semantic information is represented as a blue seat, the part of landmark information is updated to a blue seat of length x, width y, and height z), and meanwhile, the part of map is a semantic map added on the basic point cloud map.
Therefore, in the navigation process of the robot, the map optimization operation is carried out in real time, and the main optimization contents comprise: the current map precision, the path track bound in the map and the semantic information in the map. Specifically, the higher-dimensionality landmark information is used as important observation information used in optimization, and joint optimization is performed on the whole map and the track pose of the robot. Semantic information of the current environment, path track information of the robot, various service operation information of the robot and various state information of the robot are jointly recorded, and a map with higher precision is constructed through analysis and optimization, so that the robot can play a greater value in production and life.
Preferably, during the robot navigation, the method may further include: extracting point cloud information based on boundary information of a deep semantic map, fitting the extracted point cloud information into point cloud cluster sets in a clustering mode, and determining a centroid point of each point cloud cluster set; calculating Euclidean distances between the robot and other centroid points except the at least one centroid point in the plurality of centroid points according to a first position relation among the centroid points in the semantic map and the Euclidean distance between the robot and the at least one centroid point in the plurality of centroid points; and comparing the calculated Euclidean distance with the current actual distance information, and if the deviation is greater than a preset deviation threshold value, executing corresponding decision processing to enable the robot to return to the path to be tracked.
In the preferred implementation process, the point cloud information may be extracted based on the boundary information of the super point cloud information, the extracted point cloud information may be fitted to the point cloud cluster sets in a clustering manner (e.g., k-means clustering algorithm, etc.), and the centroid points of each of the point cloud cluster sets may be determined, as described above, the stable result finally determined by the k-means clustering algorithm may be used as the centroid points of the point cloud cluster sets. For example, three objects (which may be tea tables, chairs, stools, etc.) in a semantic map, each centroid point is taken as a central representative point of one object, the euclidean distance of the robot with respect to the centroid point 3 can be calculated according to the euclidean distance between the current centroid point 1 and the centroid point 2 of the robot and the position relationship between the centroid points 1, 2, 3, if the calculated euclidean distance is 3 meters, and according to the trajectory of the path to be tracked, the actual distance information should be 2.8 meters, and the offset amount of 0.2 meter is greater than a preset offset threshold value (for example, 0.1 meter), optimization needs to be performed according to the two distance parameters and all current observation information, and the navigation strategy of the robot is adjusted according to the optimization result, for example, the path is adjusted according to the calculated offset so that the robot returns to the path to be tracked.
Therefore, whether the robot deviates from the path to be tracked can be determined according to the position relation among the objects in the semantic map, when the robot deviates from the path to be tracked, the autonomous navigation path of the robot can be adjusted in time, the robot is prevented from running to a dangerous area, and therefore the safety of the robot is guaranteed.
Preferably, before the robot navigation, the following processes may be further included: responding to a first operation instruction of a user, and respectively binding business operations (such as rotation, arm action, water spraying, dust absorption, detouring, corresponding equipment opening and the like) corresponding to one or more pieces of position information on the path to be tracked, wherein the path to be tracked is a path preset by the user, a path on which the robot is operated in advance by the user to execute tasks, a path planned in advance by the robot, or a path updated by last navigation.
For example, when a user uses a remote controller to control a robot to perform a task for the first time, a virtual wall or a fragile object (for example, a vase and the like) is arranged in a front predetermined range on a position 1 of a path to be tracked, information of the position 1 (for example, coordinate position information in a world coordinate system) is bound with a detour business operation, and the binding relationship is recorded and stored. In the subsequent autonomous navigation process of the robot, when the robot is judged to travel to the position, business operation bound with the position is executed, and the bypassing operation is executed on the virtual wall or the fragile object according to a preset bypassing strategy.
Preferably, after the service operation corresponding to the location information is bound, the method may further include: the robot determines a first binding relationship between the business operation and a corresponding scene in the map information; and for the updated map information, the robot automatically increases or removes the current binding relationship between one or more pieces of position information on the path to be tracked and the corresponding business operation according to the first binding relationship.
In an optimal implementation process, the robot may also learn a binding relationship between the position and the business operation, autonomously establish a new binding relationship between the position and the business operation, or delete an existing binding relationship between the position and the business operation, for example, in an autonomous navigation process of the robot, continuously optimize and update a current semantic map, when another fragile object (for example, a vase and the like) newly appears in a current scene due to a change of an environment, the robot determines a belonging object classification set according to the class information of the object, when it is determined that the object belongs to the fragile object class, the robot automatically increases the binding relationship between the position 2 and the detour operation according to the learned binding relationship before reaching the position 2 before the fragile object, and records and stores the binding relationship. In the next autonomous navigation process, when the robot reaches the position 2, a detour operation is triggered, the detour operation is executed, and local optimization adjustment is executed on a path to be tracked. In the preferred implementation process, the optimized path can be used as a new path to be tracked, and is bound in the map information again to be used as the path to be tracked for the next robot navigation.
In addition, the robot learns the binding relationship between the position and the service operation, and can autonomously delete (remove) the binding relationship between the current existing position and the service operation besides autonomously establishing a new binding relationship between the position and the service operation. For example, in the autonomous navigation process of the robot, the current semantic map is continuously optimized and updated, and due to the change of the environment, when the robot detects that the fragile object disappears in the current scene, the binding relationship between the position 2 and the detour operation is automatically released. In the next autonomous navigation process, when the robot reaches the position 2, the bypassing operation is not executed any more, the local optimization adjustment is executed on the path to be tracked again, and the optimized path is used as a new path to be tracked and is bound in the three-dimensional point cloud map and/or the semantic map again to be used as the path to be tracked for the next robot navigation.
Preferably, before the robot navigation, the following processes may be further included: and responding to a second operation instruction of the user, and respectively binding state information (for example, a slipping state, a water shortage state, a power shortage state and the like) corresponding to each piece of position information in at least one piece of position information on the path to be tracked.
Preferably, after binding the state information corresponding to the location information, the method may further include: and for the second position information bound with the state information, when the distance between the robot and the second position information is smaller than a preset distance threshold value in the process that the robot moves to the second position information, executing corresponding decision processing in advance according to the state information.
In a preferred implementation process, when a user uses a remote controller to operate the robot to perform a task, the state information of the robot and the position information corresponding to the state information are obtained in real time, for example, when it is determined that the wheeled robot runs to a position 3, a slip occurs, which indicates that in the position 3, the robot is in a special state, and then a binding relationship between the position 3 and the slip state information is established. In the process of the next autonomous navigation of the robot, when the robot runs to the corresponding position before the position 3, parameters adaptive to a special scene can be adjusted according to the existing state information, so that the robot still has higher positioning accuracy and running fluency in the special scene. For example, when a robot slips, the reliability of the observation data of a sensor (for example, an odometer or the like) that is greatly affected by the slip state is lowered, and the reliability of the observation data of a sensor (for example, an IMU or the like) that is less affected by the slip state is increased.
Preferably, after the status information corresponding to the location information is bound, the following processing may be further included: the robot determines a second binding relationship between the state information and a corresponding scene in the map information; and for the updated map information, the robot automatically increases or removes the current binding relationship between one or more pieces of position information on the path to be tracked and the corresponding state information according to the second binding relationship.
In the preferred implementation process, the robot can also learn the binding relationship between the position and the state information, autonomously establish a new binding relationship between the position and the state information or delete the existing binding relationship between the position and the state information, for example, in the autonomous navigation process of the robot, continuously optimize and update the current semantic map, due to the change of the environment, a new groove appears in the current scene, the wheels of the wheeled robot are clamped between the grooves, and when the robot determines that a slip state appears, the robot automatically increases the binding relationship between the current position 4 and the slip state information according to the learned binding relationship, and records and stores the binding relationship. In the next autonomous navigation process, when the robot reaches the position 4, the reliability of the observation data of the sensor (for example, an odometer or the like) that is greatly affected by the slip state is lowered, and the reliability of the observation data of the sensor (for example, an IMU or the like) that is less affected by the slip state is increased. Alternatively, other corresponding decision strategies may also be implemented, such as speeding up or slowing down the backoff to get rid of the trap, etc.
In addition, the robot learns the binding relationship between the position and the state information, and can independently delete (release) the binding relationship between the current position and the state information in addition to independently establishing a new binding relationship between the position and the state information. For example, in the autonomous navigation process of the robot, the current semantic map is continuously optimized and updated, and when the robot detects that the groove in the current scene disappears due to the change of the environment, the binding relationship between the position 4 and the slip state information is automatically released. In the next autonomous navigation process, when the robot reaches the position 4, the reliability of the observation data of the sensor (for example, an odometer or the like) greatly affected by the slip state is improved.
In summary, based on a three-dimensional point cloud map or a multi-layer semantic map (a first-layer world map, a second-layer shallow-layer semantic map, and a third-layer deep-layer semantic map) created by a world coordinate system, when a user operates a robot in advance to perform a task (for example, operates the robot in a remote controller operation manner), and the like, after all robot states and observation information are obtained, the tracks and the observation information of the robot operation are corrected and fused, and are bound to the current map of the robot, and simultaneously, navigation information, semantic information, robot service operation information, and state information are fused and bound with the current robot operation track, so that a more accurate robot state estimation result and a robot positioning obstacle avoidance map are obtained.
For the map fused with various information, the robot carries out real-time optimization on the current map in the autonomous navigation process, and the main optimization comprises the following steps: the accuracy of the currently created map, the track pose recorded in the map and the semantic information in the map. The method specifically comprises the steps of performing joint optimization on the whole map and the track pose of the robot by using higher-dimension landmark information (point cloud cluster set) as important observation information used in optimization, and correcting other information in the map by using the correction result of the running pose track of the robot and the relative relation between the recorded states of the landmarks and the pose of the robot.
After a map fused with multiple information is created and optimized, the map can be stored, a corresponding map can be selected according to a scene, and the map is used for the next navigation and positioning work of the robot.
According to the embodiment of the invention, a robot business operation execution device is provided.
Fig. 2 is a block diagram of a robot-executing business operation apparatus according to an embodiment of the present invention. As shown in fig. 2, the robot execution service operation apparatus includes: a map updating module 20, configured to dynamically update map information established based on a world coordinate system when the robot performs navigation; an obtaining module 22, configured to obtain current pose data of the robot, and obtain current position information of the robot in a world coordinate system according to the pose data; and the execution module 24 is configured to determine whether the current location information corresponds to first location information in a world coordinate system on a path to be tracked, and if so, execute a service operation bound with the first location information, where one or more pieces of location information on the path to be tracked are respectively bound with corresponding service operations, the one or more pieces of location information include the first location information, and the path to be tracked is bound in the map information.
By adopting the device shown in fig. 2, in the process of navigating the robot according to the path to be tracked, the map updating module 20 dynamically updates the map information established based on the world coordinate system, constructs a map with higher precision through real-time analysis and optimization, and combines the positioning function according to the high-precision map and the robot, so that the robot can be prevented from running to a dangerous area, and the safety of the robot is improved. Moreover, since the path to be tracked is bound in the map information, one or more pieces of location information on the path to be tracked are respectively bound with corresponding business operations (for example, businesses such as rotating, bypassing, or performing water spraying), when the robot travels to the location where the business operations are bound, the execution module 24 may execute the business operations corresponding to the location, thereby completing various work tasks more intelligently during the autonomous navigation process.
It should be noted that, in the above preferred embodiment in which the modules in the robot service execution device are combined with each other, reference may be made to corresponding relevant description and effects in the embodiment of fig. 1 for understanding, and details are not described here again.
According to an embodiment of the present invention, a robot is provided.
Fig. 3 is a block diagram of a robot according to an embodiment of the present invention. As shown in fig. 3, the robot according to the present invention includes: a memory 30 and a processor 32, wherein the memory 30 is used for storing computer execution instructions; the processor 32 is configured to execute the computer-executable instructions stored in the memory, so that the robot executes the robot service operation method provided in the embodiment.
Processor 32 may be a Central Processing Unit (CPU). The Processor 52 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any combination thereof.
The memory 30, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the robot repositioning method in embodiments of the present invention. The processor executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions, and modules stored in the memory.
The memory 30 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 30 optionally includes memory located remotely from the processor, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 30 and, when executed by the processor 32, perform a method of performing a business operation by a robot as in the embodiment shown in fig. 1.
The details of the robot can be understood by referring to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.
In summary, with the above-mentioned embodiments provided by the present invention, semantic information of the current environment, path trajectory information of the robot, various service operation information of the robot, and various status information of the robot are jointly recorded and bound, and a map with higher accuracy is constructed by analysis and optimization, so that service operations corresponding to positions can be executed, thereby more intelligently completing various work tasks in the autonomous navigation process, and enabling the robot to exert greater value in production and life. By fusing the map with multiple information, the robot navigation system can plan more efficiently according to historical information and correct the map according to information such as semantics and the like, so that the positioning is more accurate; meanwhile, the robot can be prevented from running to a dangerous area in the running process according to semantic information, and safety is guaranteed. The robot has a learning function, and can automatically increase or remove the binding relationship between one or more pieces of position information on the path to be tracked and the corresponding business operation according to the binding relationship between the position determined in the process of executing the task by the user or autonomously navigating the robot and the business operation, and simultaneously, can automatically increase or remove the binding relationship between one or more pieces of position information on the path to be tracked and the corresponding state information according to the binding relationship between the position determined in the process of executing the task by the user or navigating the robot and the state information, so that the robot is more intelligent and humanized.
The above disclosure is only for a few specific embodiments of the present invention, but the present invention is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present invention.
Claims (11)
1. A method for a robot to perform business operations, comprising:
in the process of robot navigation, map information established based on a world coordinate system is dynamically updated;
acquiring current position and attitude data of the robot, and acquiring current position information of the robot in a world coordinate system according to the position and attitude data;
and judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information.
2. The method of claim 1, further comprising, prior to the robot navigating:
establishing a world coordinate system, and constructing a world map based on the world coordinate system;
based on a plurality of sensor data, establishing a shallow semantic map by combining super point cloud information extracted by a deep learning algorithm, and binding the shallow semantic map with the world map.
3. The method of claim 1, further comprising, prior to the robot navigating:
establishing a world coordinate system, and constructing a world map based on the world coordinate system;
establishing a deep semantic map based on semantic information extracted by a deep learning algorithm, and binding the deep semantic map with the world map, wherein the deep semantic map comprises: boundary information, category information.
4. The method of claim 3, further comprising, during the robotic navigation:
extracting point cloud information based on boundary information of a deep semantic map, fitting the extracted point cloud information into point cloud cluster sets in a clustering mode, and determining a centroid point of each point cloud cluster set;
calculating Euclidean distances between the robot and other centroid points except the at least one centroid point in the plurality of centroid points according to a first position relation between the plurality of centroid points in the semantic map and the Euclidean distance between the robot and the at least one centroid point in the plurality of centroid points;
and comparing the calculated Euclidean distance with the current actual distance information, and if the deviation amount is greater than a preset deviation threshold value, executing corresponding decision processing to enable the robot to return to the path to be tracked.
5. The method of claim 1, further comprising, prior to the robot navigating:
and responding to a first operation instruction of a user, and respectively binding business operation corresponding to one or more pieces of position information on the path to be tracked, wherein the path to be tracked is a path preset by the user, a path on which the user operates the robot in advance to execute tasks, a path planned in advance by the robot, or a path updated by the last navigation.
6. The method of claim 5, further comprising, after binding the service operation corresponding to the location information:
the robot determines a first binding relationship between the business operation and a corresponding scene in the map information;
and for the updated map information, the robot automatically increases or removes the current binding relationship between one or more pieces of position information on the path to be tracked and the corresponding business operation according to the first binding relationship.
7. The method of claim 1, further comprising, prior to the robot navigating:
and responding to a second operation instruction of the user, and respectively binding state information corresponding to the position information for each position information in at least one position information on the path to be tracked.
8. The method of claim 7, wherein after binding the status information corresponding to the location information, further comprising:
and for the second position information bound with the state information, when the distance between the robot and the second position information is smaller than a preset distance threshold value in the process that the robot moves to the second position information, executing corresponding decision processing in advance according to the state information.
9. The method of claim 7, further comprising, after binding the status information corresponding to the location information:
the robot determines a second binding relationship between the state information and a corresponding scene in the map information;
and for the updated map information, the robot automatically increases or removes the current binding relationship between one or more pieces of position information on the path to be tracked and the corresponding state information according to the second binding relationship.
10. A robotic executive business operation device, comprising:
the map updating module is used for dynamically updating map information established based on a world coordinate system when the robot carries out navigation;
the acquisition module is used for acquiring the current position and attitude data of the robot and acquiring the current position information of the robot in a world coordinate system according to the position and attitude data;
and the execution module is used for judging whether the current position information corresponds to first position information in a world coordinate system on a path to be tracked, and if so, executing business operation bound with the first position information, wherein one or more pieces of position information on the path to be tracked are respectively bound with corresponding business operation, the one or more pieces of position information comprise the first position information, and the path to be tracked is bound in the map information.
11. A robot, comprising: a memory and a processor, wherein the memory,
the memory is used for storing computer execution instructions;
the processor to execute the memory-stored computer-executable instructions to cause the robot to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210205081.3A CN114770495A (en) | 2022-03-02 | 2022-03-02 | Robot execution business operation method and device and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210205081.3A CN114770495A (en) | 2022-03-02 | 2022-03-02 | Robot execution business operation method and device and robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114770495A true CN114770495A (en) | 2022-07-22 |
Family
ID=82423013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210205081.3A Pending CN114770495A (en) | 2022-03-02 | 2022-03-02 | Robot execution business operation method and device and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114770495A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107990899A (en) * | 2017-11-22 | 2018-05-04 | 驭势科技（北京）有限公司 | A kind of localization method and system based on SLAM |
| CN109074668A (en) * | 2018-08-02 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method for path navigation, relevant apparatus and computer readable storage medium |
| CN111798475A (en) * | 2020-05-29 | 2020-10-20 | 浙江工业大学 | Indoor environment 3D semantic map construction method based on point cloud deep learning |
| CN112799095A (en) * | 2020-12-31 | 2021-05-14 | 深圳市普渡科技有限公司 | Static map generation method and device, computer equipment and storage medium |
| WO2021233452A1 (en) * | 2020-05-22 | 2021-11-25 | 杭州海康机器人技术有限公司 | Map updating method and apparatus |
| CN113837059A (en) * | 2021-09-22 | 2021-12-24 | 哈尔滨工程大学 | Patrol vehicle for advising pedestrians to wear mask in time and control method thereof |
-
2022
- 2022-03-02 CN CN202210205081.3A patent/CN114770495A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107990899A (en) * | 2017-11-22 | 2018-05-04 | 驭势科技（北京）有限公司 | A kind of localization method and system based on SLAM |
| CN109074668A (en) * | 2018-08-02 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method for path navigation, relevant apparatus and computer readable storage medium |
| WO2020024234A1 (en) * | 2018-08-02 | 2020-02-06 | 深圳前海达闼云端智能科技有限公司 | Route navigation method, related device, and computer readable storage medium |
| WO2021233452A1 (en) * | 2020-05-22 | 2021-11-25 | 杭州海康机器人技术有限公司 | Map updating method and apparatus |
| CN111798475A (en) * | 2020-05-29 | 2020-10-20 | 浙江工业大学 | Indoor environment 3D semantic map construction method based on point cloud deep learning |
| CN112799095A (en) * | 2020-12-31 | 2021-05-14 | 深圳市普渡科技有限公司 | Static map generation method and device, computer equipment and storage medium |
| CN113837059A (en) * | 2021-09-22 | 2021-12-24 | 哈尔滨工程大学 | Patrol vehicle for advising pedestrians to wear mask in time and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109916393B (en) | Multi-grid-value navigation method based on robot pose and application thereof | |
| US10705528B2 (en) | Autonomous visual navigation | |
| CN109947120B (en) | Path planning method in warehousing system | |
| WO2021135813A1 (en) | Robot joint mapping method and device, and computer-readable storage medium | |
| CN113110455B (en) | Multi-robot collaborative exploration method, device and system for unknown initial state | |
| CN111982114B (en) | Rescue robot for estimating three-dimensional pose by adopting IMU data fusion | |
| CN111693050A (en) | Indoor medium and large robot navigation method based on building information model | |
| CN110986945B (en) | Local navigation method and system based on semantic altitude map | |
| CN115639823B (en) | Method and system for controlling sensing and movement of robot under rugged undulating terrain | |
| Wang et al. | A fuzzy logic path planning algorithm based on geometric landmarks and kinetic constraints | |
| CN108803602B (en) | Obstacle self-learning method and new obstacle self-learning method | |
| CN111176276A (en) | Development and application of intelligent warehousing robot | |
| CN113515117A (en) | Conflict resolution method for multi-AGV real-time scheduling based on time window | |
| CN114460939B (en) | Autonomous navigation improvement method for intelligent walking robot in complex environment | |
| CN114564008A (en) | Mobile robot path planning method based on improved A-Star algorithm | |
| Zhang et al. | A robot navigation system in complex terrain based on statistical features of point clouds | |
| CN111045428B (en) | Obstacle avoidance method, mobile robot, and computer-readable storage medium | |
| CN117470241A (en) | Self-adaptive map-free navigation method and system for non-flat terrain | |
| Lu et al. | Lane marking-based vehicle localization using low-cost GPS and open source map | |
| CN114770495A (en) | Robot execution business operation method and device and robot | |
| CN111912411B (en) | Robot navigation positioning method, system and storage medium | |
| Zheng et al. | Semantic map construction approach for human-robot collaborative manufacturing | |
| Meng et al. | A navigation framework for mobile robots with 3D LiDAR and monocular camera | |
| CN116625386B (en) | Map construction method and multi-robot path planning method based on image filtering | |
| US20240027224A1 (en) | Method for recognizing an erroneous map of an environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |