WO2022007754A1 - 工人位置估算方法、设备及存储介质 - Google Patents
工人位置估算方法、设备及存储介质 Download PDFInfo
- Publication number
- WO2022007754A1 WO2022007754A1 PCT/CN2021/104570 CN2021104570W WO2022007754A1 WO 2022007754 A1 WO2022007754 A1 WO 2022007754A1 CN 2021104570 W CN2021104570 W CN 2021104570W WO 2022007754 A1 WO2022007754 A1 WO 2022007754A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- worker
- time
- real
- probability
- distribution
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000003993 interaction Effects 0.000 claims abstract description 22
- 238000005516 engineering process Methods 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 11
- 230000026058 directional locomotion Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000002441 reversible effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41815—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the cooperation between machine tools, manipulators and conveyor or other workpiece supply system, workcell
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Definitions
- the invention relates to the field of robot technology, and in particular, to a method, equipment and storage medium for estimating the position of a worker.
- the application scenario includes a robot scheduling system, several robots and several workers, and the robots and workers can move independently and cooperate with each other; The robot calls to do the job; in this similar way of human-machine interaction, the robot and the worker cooperate to complete the task.
- the robot scheduling system knows the real-time position of the robot, but does not know the real-time position of the worker; therefore, in order to enable efficient linkage between the robot and the worker, and minimize the moving distance of the worker, the robot scheduling system dispatches tasks when scheduling tasks. , it is necessary to locate the position of workers in the site in real time.
- the present invention provides a method, device and storage medium for estimating a worker's position, which are used to estimate the probability of a worker's position distribution in real time on the premise that the existing site environment is not changed and that the worker does not wear any positioning device.
- the present invention provides a method for estimating a worker's position, and the method for estimating a worker's position includes:
- the real-time location of the worker in the workplace is estimated.
- the present invention provides a worker position estimation device, the worker position estimation device includes a position acquisition module, a probability map generation module, and a worker position estimation module, wherein:
- the position obtaining module is set to: at the beginning of each work stage, obtain the initial position of the worker corresponding to the worker entering the designated position in advance; monitor the human-machine interaction event between the robot and the worker in real time, and obtain the real-time position information of the robot ;
- the probability map generation module is set to: based on the obtained initial position of the worker and the real-time position information of the robot, according to preset time intervals, obtain the worker distribution probability that a worker exists at each location point in the workplace, and generate all the worker distribution probabilities.
- the worker position estimation module is configured to: estimate the real-time position of the worker in the workplace based on the generated real-time probability map.
- the present invention provides an electronic device comprising a memory and a processor, the memory storing a worker position estimation program executable on the processor, the worker position estimation program being When the processor is running, the worker position estimation method is executed.
- the present invention provides a computer-readable storage medium on which a worker position estimation program is stored, and the worker position estimation program can be executed by one or more processors to implement the worker position estimation program. Steps of the location estimation method.
- the present invention provides a method, equipment and storage medium for estimating the position of a worker. By obtaining the initial position of the worker corresponding to the designated location point of the worker at the beginning of each work stage, the human-machine interaction event between the robot and the worker is monitored in real time.
- FIG. 1 is a schematic flowchart of an embodiment of a worker position estimation method of the present invention.
- FIG. 2 is a schematic diagram of a probability model of an embodiment corresponding to the probability distribution of the worker's location in the worker location estimation method of the present invention.
- Fig. 3 is a real-time probability map represented by contour lines in an embodiment corresponding to the probability distribution of the worker's location in the worker's location estimation method of the present invention.
- FIG. 4 is a schematic diagram of a signal flow of a working scene of an embodiment of an application scene in the worker position estimation method of the present invention.
- FIG. 5 is a schematic diagram of functional modules of an embodiment of the worker position estimation device of the present invention.
- FIG. 6 is a schematic diagram of the internal structure of an embodiment of the electronic device of the present invention.
- the present invention provides a method, equipment and storage medium for estimating the position of workers, which are used to estimate the position distribution probability of workers in real time under the premise that the existing site environment is not changed and the workers do not wear any positioning equipment, and realize the efficient and low-cost realization of workers. Worker positioning in the scenario of cooperating with robot clusters to improve the synergy between robots and workers.
- the method for estimating a worker's position includes steps S10-S40.
- Step S10 At the beginning of each work stage, obtain the initial position of the worker corresponding to the point where the worker enters the designated position in advance.
- the robot scheduling system obtains the corresponding The initial position of the worker, and then, the real-time location of the worker will be obtained by the robot that cooperates with the worker, that is, the robot scheduling system can obtain the location information of the worker who cooperates with the robot through the location information of the robot carried in the communication data sent by the robot. .
- Step S20 monitoring human-computer interaction events between the robot and the worker in real time, and acquiring real-time position information of the robot.
- the robot scheduling system can obtain the robot by monitoring the human-computer interaction between the robot and the worker in real time. real-time location information. For example, when the robot reaches a certain point A in the workplace, it starts to cooperate with the workers to execute the corresponding human-computer interaction event to complete the corresponding work task. At this time, when the robot reaches the point A, the The robot scheduling system can obtain the position point A of the robot at this moment by interacting with the data of the robot, and then according to the current position point A of the robot, the robot scheduling system can obtain the man-machine interaction with the robot at this moment. The real-time location of interacting workers.
- Step S30 Based on the obtained initial position of the worker and the real-time position information of the robot, according to preset time intervals, obtain the worker distribution probability that a worker exists at each location point in the workplace, and generate the corresponding worker distribution probability. Visualized real-time probability plots.
- Step S40 based on the generated real-time probability map, estimate the real-time position of the worker in the workplace.
- the robot scheduling system acquires real-time position information of each robot while interacting with the robots working in the workplace. At the same time, using the initial positions of the workers obtained at the beginning of each work stage, the robot scheduling system obtains the distribution probability of workers that there are workers at each location in the workplace within each preset time interval.
- the preset time interval can be specifically set according to specific application scenarios, workplaces, task types of human-machine interaction between the robot and the worker, etc. The specific value of the preset time interval is not limited in the implementation of the present invention.
- the robot scheduling system in order to display more intuitively for system scheduling and/or background monitoring, the robot scheduling system generates a visualized real-time probability map corresponding to the worker distribution probability, such as heat map, probability distribution curve, etc. Using the generated real-time probability map, the corresponding real-time position of the worker in the workplace at the corresponding moment can be estimated at a glance.
- the robot scheduling system when the robot scheduling system generates a real-time probability map, it can be realized by using the application principle of probability time geography in positioning technology.
- Probabilistic temporal geography is: on the basis of the reachable range determined by temporal geography, analyzing the possibility of the location of the moving object can provide a quantitative basis for the maximum possible positioning of the moving object.
- step S30 in the embodiment shown in FIG. 1 may be implemented according to the following technical means:
- the probability distribution of the location of the worker satisfies the probability model of a two-dimensional normal distribution; using the probability model, according to the preset time interval ⁇ T , obtain the worker distribution probability of the presence of workers at each location point in the workplace, and generate the visualized real-time probability map in the form of contour lines.
- (x, y) obey the two-dimensional normal distribution of parameters ⁇ 1, ⁇ 2, s1, s2 and ⁇ ; wherein, the parameters ⁇ 1, ⁇ 2, s1, s2 and ⁇ are all constants , whose value ranges are: ⁇ 1 ⁇ 0; ⁇ 2 ⁇ 0; -1 ⁇ 1; - ⁇ 1 ⁇ + ⁇ ; - ⁇ 2 ⁇ + ⁇ .
- the plane area that the worker can reach within the unit time T with the maximum walking speed V can be represented by a circle, also called the potential area. (potential path area, PPA).
- PPA potential path area
- the probability distribution of the location of the worker conforms to the probability model of the two-dimensional normal distribution, that is, the probability model corresponding to the mathematical expression (1).
- ⁇ 1, ⁇ 2, s1, s2 and ⁇ are all constants, and (x, y) is said to obey the two-dimensional normal distribution of parameters ⁇ 1, ⁇ 2, s1, s2 and ⁇ .
- Fig. 2 is a schematic diagram of a probability model of an embodiment corresponding to the probability distribution of the worker's position in the worker position estimation method of the present invention; the function of the mathematical expression (1) corresponding to the probability model is in a three-dimensional space The image is an oval cut bell upside down on a plane, as shown in Figure 2.
- the parameters s1 and s2 of the normal distribution in the probability model are proportional to the walking speed of the worker, that is, the greater the walking speed of the worker, the greater the variance corresponding to the normal distribution in the probability model.
- the probability model is used to obtain the worker distribution probability of the presence of workers at each location in the workplace according to the preset time interval ⁇ T, And generate the visualized real-time probability map in the form of contour lines, which can be implemented by the following technical means:
- the global operation corresponding to the workplace is performed to obtain the worker distribution probability that there are workers at each location in the workplace; based on the probability model, by dividing the vertical The z-axis of the direction is removed, and only the x-axis and the y-axis are retained, and the three-dimensional image of the three-dimensional space corresponding to the probability model is converted into a two-dimensional space.
- the real-time probability map representing the distribution probability of the workers in the form of; wherein, the value corresponding to each circle in the real-time probability map is the probability of workers appearing here.
- FIG. 3 is a real-time probability map represented by a contour line corresponding to an embodiment of the probability distribution of the worker's location in the worker location estimation method of the present invention; if a two-dimensional normal The image of distribution is such as the three-dimensional image shown in Figure 2, the Z axis is removed, and the probability value of the distribution of workers in the workplace is represented in the form of contour lines, then for the images of D1 and D2, it becomes a series of The circle of , and the value corresponding to each circle corresponds to the probability of the worker appearing here.
- the movement direction of the workers in the workplace is not random, and when the movement direction of the workers is not random, the Maxwell-Boltzmann distribution law is introduced as the The expansion of the probability model means that at any moment in the unit time T, the probability model corresponding to the probability distribution of the worker's location evolves into a probability model based on normal distribution for directional movement.
- the Maxwell-Boltzmann distribution law is introduced as the An extension of the probabilistic model described above. Since the Maxwell-Boltzmann distribution law holds for any particle of matter (gases, liquids, atoms and molecules of solids, Brownian particles, etc.), moving in any conservative force field, Brownian particles are regarded as giant molecules . In temporal geography, on the one hand, people have the diffusion characteristics of particles. For example, in order to avoid task congestion and deployment, workers tend to move to relatively loose areas to stand by.
- the robot scheduling system further has the function of feedback adjustment.
- the worker position estimation method further includes:
- the robot cluster and/or task scheduling in the work site is reversely regulated.
- the real-time probability map intuitively shows the corresponding distribution probability of workers in the workplace at each moment, the peak distance of the contour line and the distribution tightness of the contour curve can be used to know the workplace at different times. the situation of internal workers.
- the real-time probability map of worker distribution probability it is possible to reversely control the robot clusters working in the workplace and/or perform task scheduling.
- the robot scheduling system reversely regulates the robot cluster and/or task scheduling in the workplace according to the generated real-time probability map in the form of contour lines, and may follow the following technical means Implementation:
- the robot scheduling system detects that the peak points of the contour lines are very close (that is, the The peak points are close to each other), and the contour curve distribution is too tight (that is, the parameters s1 and s2 of the normal distribution are too small), it means that the current tasks in the workplace are too concentrated in one place.
- an appropriate threshold can be set according to the peak point distance and the curve density. For example, the corresponding preset distance is set for the peak point distance, and the corresponding preset density is set for the curve density of the contour line.
- the robot scheduling system Start to perform reverse regulation and rearrange the scheduling of robot clusters, such as taking measures such as decentralizing tasks and decentralizing worker positions.
- the robot scheduling system detects that the contour curve distribution is too loose (that is, the parameters s1 and s2 of the normal distribution are too large), for example, the curve density between the above contour curves is lower than the preset threshold, it means that the current There are currently fewer tasks that can be performed in the workplace.
- the robot scheduling system starts to perform reverse regulation, and according to the real-time probability map, rearranges the tasks of the workers in the workplace; for example, setting the workers' rest time to allow some workers to take turns to leave their posts to rest; or Yes, adjust the travel speed V of the workers to reduce the parameters s1 and s2.
- different implementations may be selected according to specific requirements.
- the embodiments of the present invention mainly describe the inventive concepts and ideas of the present invention.
- specific settings and configurations can be performed according to different application scenarios and different workplaces, and the embodiments of the present invention do not list them all one by one. and elaboration.
- the method for estimating the position of the worker in the embodiment of the present invention achieves the purpose of estimating the probability of the location distribution of the worker in real time without changing the existing site environment and the worker does not wear any positioning equipment, makes full use of resources, and achieves high efficiency and low cost.
- the beneficial effect of human-computer interaction is realized at a low cost, and the synergy between human and computer is also improved.
- FIG. 4 is a schematic diagram of a signal flow of a working scene of an embodiment of an application scene in the method for estimating the worker position of the present invention.
- the work scenario shown in FIG. 4 operates based on the idea of the worker position estimation method described in the present invention.
- the system operating environment corresponding to the worker position estimation method of the present invention is based on a stream computing model. system; its main job is to use the location information in the interactive information between the robot and the worker as the flow entry, and use the worker location estimation method to generate the probability distribution corresponding to the worker location in real time; and then use the real-time probability distribution corresponding to the worker location probability distribution.
- the graph serves as the basis for robot swarms and/or task scheduling.
- the original positioning module of the robot and the original system process of the robot scheduling system are used, the hardware layout of the warehouse is not changed, and there is no need to add additional positioning equipment to the workers, and the existing
- the communication data between the robot scheduling system and the robot can realize the density corresponding to the worker position estimation method, device and storage medium of the present invention.
- the communication data between the robot and the robot dispatching system contains the position information of the human-machine interaction, that is, the position of the worker when a worker cooperates with the robot at a certain moment, so the robot dispatching system actually passes the robot
- the data of the worker's appearance position is continuously received, and the main idea of the present invention is to make full use of the data of the worker's appearance position continuously obtained by the robot scheduling system through the robot, and use the present invention to estimate the worker's position.
- Algorithms suitable for specific application scenarios corresponding to the method, equipment and storage medium are used to calculate the worker distribution probability.
- the robot scheduling system can also perform reverse adjustment based on the obtained real-time worker distribution probability to perform optimal scheduling of the workplace, such as arranging new jobs, thereby generating new human-machine interactions and generating new data streams; In this way, it can enter the forward data cycle and the continuous operation of the robot scheduling system.
- the robot scheduling system in the application scenario shown in FIG. 4 utilizes the existing human-computer interaction signals, and uses the stream computing framework to estimate the worker position in real time through the worker position estimation method, device and storage medium of the present invention. Location distribution, and based on this, the robot cluster and/or task scheduling can be regulated to achieve the purpose of efficiently and low-costly realizing the location of the worker in the scenario of cooperation between the robot and the worker, and improve the synergy between the robot and the worker.
- an embodiment of the present invention further provides a device for estimating a worker's position, including:
- the position obtaining module 100 is set to: at the beginning of each working stage, obtain the initial position of the worker corresponding to the worker entering the designated position in advance; monitor the human-machine interaction events between the robot and the worker in real time, and obtain the real-time position information of the robot ;
- the probability map generation module 200 is set to: based on the obtained initial position of the worker and the real-time position information of the robot, according to preset time intervals, obtain the distribution probability of workers that there is a worker at each location point in the workplace, and generate all the probability maps.
- the worker position estimation module 300 is configured to: estimate the real-time position of the worker in the workplace based on the generated real-time probability map.
- the worker position estimation device is further configured to:
- the task scheduling algorithm is optimized, the robot is dispatched to the optimal task range corresponding to the real-time probability map, and when the robot and the worker complete the interactive operation, the robot receives the robot's transmission.
- the robot receives the robot's transmission.
- the probability map generation module 200 is set to: using the application principle of probability time geography in positioning technology, at any time in the unit time T, the probability distribution of the location of the worker satisfies the two-dimensional normal distribution Probability model; using the probability model, according to the preset time interval ⁇ T, obtain the worker distribution probability of the presence of workers at each location point in the workplace, and generate the visualized real-time probability map in the form of contour lines.
- the probability map generation module 200 is set to: in the case that the movement direction of the worker is random, using the application principle of probability time geography in the positioning technology, at any moment in the unit time T, the probability of the location of the worker.
- the probability model corresponding to the distribution can be expressed as mathematical expression (1):
- (x, y) obey the two-dimensional normal distribution of parameters ⁇ 1, ⁇ 2, s1, s2 and ⁇ ; wherein, the parameters ⁇ 1, ⁇ 2, s1, s2 and ⁇ are all constants , whose value ranges are: ⁇ 1 ⁇ 0; ⁇ 2 ⁇ 0; -1 ⁇ 1; - ⁇ 1 ⁇ + ⁇ ; - ⁇ 2 ⁇ + ⁇ .
- the probability map generating module 200 is configured to: use the probability model to perform a global operation corresponding to the workplace according to a preset time interval ⁇ T, and obtain that there are workers at each location in the workplace Existing worker distribution probability; based on the probability model, by removing the z-axis in the vertical direction and retaining only the x-axis and y-axis, the three-dimensional image of the three-dimensional space corresponding to the probability model is converted into a two-dimensional space. Plane graphics to obtain a series of the real-time probability maps containing circles and representing the distribution probability of the workers in the form of contour lines; wherein, the value corresponding to each circle in the real-time probability map is the worker appearing in the probability here.
- the probability map generation module 200 is set to: in the case that the movement direction of the worker is not random, the Maxwell-Boltzmann distribution law is introduced as an extension of the probability model, then the probability within the unit time T is At any time, the probability model corresponding to the probability distribution of the worker's location evolves into a probability model based on normal distribution for directional movement.
- the worker position estimating device is configured to reversely regulate the robot cluster and/or task scheduling in the workplace according to the generated real-time probability map in the form of contour lines.
- the worker position estimation device is configured to: analyze the real-time probability map according to the generated real-time probability map in the form of contour lines; The distance between the peak points of the contour line is lower than the preset distance, and/or the curve distribution density of the contour line reaches the preset density, then according to the peak point distance of the contour line and the curve distribution density, rearrange the The tasks to be performed in the work site are to be dispersed in order to disperse the positions of workers; if it is detected that the curve distribution density of the contour lines in the real-time probability map is lower than the preset threshold, then according to the real-time probability map, Workers perform task rearrangement.
- the worker position estimation device of the present invention has all the functions of the robot scheduling system described in the above embodiments, and the specific implementation methods are basically the same as the implementation principles of the embodiments corresponding to the above worker position estimation methods, and will not be described here.
- the worker position estimation device of the invention achieves the purpose of estimating the position distribution probability of workers in real time without changing the existing site environment and the workers do not wear any positioning equipment, fully utilizes resources, and achieves efficient and low-cost realization.
- the beneficial effect of human-computer interaction also improves the synergy of human-computer.
- the present invention also provides an electronic device that can estimate the real-time location of a worker in a workplace according to the worker location estimation described in FIG. 1 .
- FIG. 6 is a schematic diagram of the internal structure of an embodiment of the electronic device of the present invention.
- the electronic device shown in Fig. 6 can estimate the position distribution probability of the workers in real time without changing the existing site environment and the workers do not wear any positioning devices, so as to efficiently and cost-effectively realize the workers in the scenario of cooperation between the workers and the robot cluster. position.
- the electronic device 1 may be a PC (Personal Computer, personal computer), or may be a terminal device such as a smart phone, a tablet computer, or a portable computer.
- the electronic device 1 includes at least a memory 11 , a processor 12 , a communication bus 13 , and a network interface 14 .
- the memory 11 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (eg, SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, and the like.
- the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk of the electronic device 1 .
- the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (Smart Media Card, SMC), Secure Digital, SD) card, flash card (Flash Card), etc.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
- the memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as codes of the worker position estimation program 01, etc., but also can be used to temporarily store data that has been output or will be output.
- the processor 12 may be a central processing unit (Central Processing Unit) in some embodiments.
- Central Processing Unit Central Processing Unit
- CPU central processing unit
- controller microcontroller
- microprocessor or other data processing chips for running program codes or processing data stored in the memory 11, for example, executing the worker position estimation program 01 and the like.
- the communication bus 13 is used to realize the connection communication between these components.
- the network interface 14 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.
- a standard wired interface such as a WI-FI interface
- WI-FI interface wireless interface
- the electronic device 1 may further include a user interface, and the user interface may include a display (Display), an input unit such as a keyboard (Keyboard), and an optional user interface may also include a standard wired interface and a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) Touch, etc.
- the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
- FIG. 6 only shows the electronic device 1 having the components 11-14 and the worker position estimation program 01.
- FIG. 6 does not constitute a limitation on the electronic device 1, and may include Fewer or more components are shown, or some components are combined, or a different arrangement of components.
- the memory 11 stores the worker position estimation program 01 ; the worker position estimation program 01 stored in the memory 11 can be stored in the processor 12 When the worker position estimation program 01 is executed by the processor 12, the steps of the above-mentioned worker position estimation method are implemented. :
- the specific implementation of the electronic device in the embodiment of the present invention is basically the same as the implementation principle of each embodiment corresponding to the above-mentioned method for estimating the worker's position. .
- an embodiment of the present invention also provides a computer storage medium, where a worker position estimation program is stored thereon, and the worker position estimation program can be executed by one or more processors, so as to realize the above-mentioned worker position estimation steps of the method.
- embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.
- the method, device and storage medium for estimating the worker's position provided by the present invention can obtain the initial position of the worker corresponding to the worker's pre-entry to the designated location point at the beginning of each work stage; monitor the human-machine interaction events between the robot and the worker in real time.
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
- Manipulator (AREA)
Abstract
一种工人位置估算方法、设备及存储介质，方法包括：在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置(S10)；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息(S20)；基于获取的工人初始位置和机器人的实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成工人分布概率对应的可视化的实时概率图(S30)；基于生成的实时概率图，估算工作场地中工人的实时位置(S40)；从而达到在不改变现有场地环境以及工人不佩戴任何定位设备的前提下、实时估算工人的位置分布概率的目的。
Description
本发明涉及机器人技术领域，特别涉及一种工人位置估算方法、设备及存储介质。
随着机器人技术的发展，机器人和人类工人进行配合工作变得越来越普遍。比如，在一个典型的应用场景中，该应用场景包括机器人调度系统、若干个机器人和若干名工人，机器人和工人能够各自移动并相互配合；例如，机器人到达指定区域并呼叫附近的工人，工人根据机器人的呼叫进行作业；通过这种类似的人机交互的方式，机器人和工人进行合作来完成任务。由于机器人调度系统已知机器人的实时位置，但未知工人的实时位置；因此，为了使机器人与工人之间能够进行高效的联动，且最大程度地减少工人的移动距离，机器人调度系统在调度任务时，需要实时定位场地内工人的位置。
现有的工人定位技术基本上均需要为工人配备相应的定位装置，也有些是为工作场地或机器人配备激光传感器、红外传感器等众多传感器，还有的甚至为此而改造场地环境。但是，如果工人数量众多、作业场地面积很大，那么就会对定位设备和传感器的精度都有很高要求，如此一来，势必大幅度增加了经济成本，也增加了工人的管理成本。为此，如何提供一种行之有效且成本低廉的工人定位方法，是目前人机交互场景所遇到的挑战之一。
本发明提供一种工人位置估算方法、设备及存储介质，用以在不改变现有场地环境以及工人不佩戴任何定位设备的前提下，实时估算工人的位置分布概率。
第一方面，本发明提供了一种工人位置估算方法，所述工人位置估算方法包括：
在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；
实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；
基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；
基于生成的所述实时概率图，估算工作场地中工人的实时位置。
第二方面，本发明提供了一种工人位置估算装置，所述工人位置估算装置包括位置获取模块、概率图生成模块以及工人位置估算模块，其中：
所述位置获取模块设置为：在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；
所述概率图生成模块设置为：基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；
所述工人位置估算模块设置为：基于生成的所述实时概率图，估算工作场地中工人的实时位置。
第三方面，本发明提供了一种电子设备，所述电子设备包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的工人位置估算程序，所述工人位置估算程序被所述处理器运行时，执行所述的工人位置估算方法。
第四方面，本发明提供了一种计算机可读存储介质，所述存储介质上存储有工人位置估算程序，所述工人位置估算程序可以被一个或者多个处理器执行，以实现所述的工人位置估算方法的步骤。
本发明一种工人位置估算方法、设备及存储介质，通过在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；基于生成的所述实时概率图，估算工作场地中工人的实时位置；达到了在不改变现有场地环境以及工人不佩戴任何定位设备的前提下、实时估算工人的位置分布概率的目的，充分利用了资源，达到了高效、低成本地实现人机交互的有益效果，同时也提高了人机的协同性。
附图用来提供对本发明的进一步理解，并且构成说明书的一部分，与本发明的实施例一起用于解释本发明，并不构成对本发明的限制。在附图中：
图1是本发明工人位置估算方法的一种实施方式的流程示意图。
图2是本发明工人位置估算方法中工人所在位置概率分布对应的一种实施方式的概率模型示意图。
图3是本发明工人位置估算方法中工人所在位置概率分布对应的一种实施方式的等高线表示的实时概率图。
图4是本发明工人位置估算方法中应用场景的一种实施方式的工作场景信号流示意图。
图5是本发明工人位置估算装置的一种实施方式的功能模块示意图。
图6是本发明电子设备的一种实施方式的内部结构示意图。
以下结合附图对本发明的优选实施例进行说明，应当理解，此处所描述的优选实施例仅用于说明和解释本发明，并不用于限定本发明。
本发明提供一种工人位置估算方法、设备及存储介质，用以在不改变现有场地环境以及工人不佩戴任何定位设备的前提下，实时估算工人的位置分布概率，高效、低成本地实现工人与机器人集群合作场景下的工人定位，提高机器人和工人之间的协同性。
如图1所示，本发明实施例的工人位置估算方法包括步骤S10-S40。
步骤S10、在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置。
本发明实施例中，在每个工作阶段的初始时，工人进入预先指定的位置点，工人的初始位置将作为机器人调度系统的初始参数；因此，机器人调度系统获取工人预先进入位置点所对应的工人初始位置，随后，工人的实时位置将通过与工人协作的机器人获取，即该机器人调度系统可以通过机器人发送的通信数据中携带的该机器人的位置信息，获取与该机器人协作的工人的位置信息。
步骤S20、实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息。
本发明实施例中，由于机器人调度系统在机器人工作的时候，二者是实时交互且有通信数据的传输，因此，机器人调度系统可以通过实时监控机器人与工人之间的人机交互操作，获取机器人的实时位置信息。比如，当机器人到达工作场地中的某位置点A时，开始与工人一起协作执行对应的人机交互事件，从而完成对应个工作任务，此时，当机器人到达该位置点A这一时刻，该机器人调度系统通过与机器人的数据交互，即可获取这一时刻机器人位于该位置点A，进而根据机器人当前所处的位置点A，该机器人调度系统便能够获取在这一时刻与机器人进行人机交互的工人的实时位置。
步骤S30、基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图。
步骤S40、基于生成的所述实时概率图，估算工作场地中工人的实时位置。
所述机器人调度系统在与工作场地中工作的机器人进行数据交互的同时，获取各机器人的实时位置信息。同时，利用在每个工作阶段的初始时获取的所述工人初始位置，所述机器人调度系统在每个预设时间间隔内，获取工作场地中每个位置点有工人存在的工人分布概率。所述预设时间间隔可以根据具体的应用场景、工作场地、机器人与工人的人机交互的任务类型等，进行具体设置，本发明实施对所述预设时间间隔的具体取值不进行限定。
根据获取到的所述工人分布概率，为了更加直观地进行显示以便于系统调度和/或后台监控，所述机器人调度系统生成所述工人分布概率对应的可视化的实时概率图，比如热点图、概率分布曲线图等。利用生成的所述实时概率图，即可一目了然地估算得知在对应的时刻，该工作场地内工人对应的实时位置。
优选地，在一个实施例中，所述机器人调度系统在生成实时概率图时，可以利用概率时间地理在定位技术上的应用原理来实现。概率时间地理即：在时间地理确定的可达范围基础上，分析移动对象所在位置的可能性，能够为移动对象最大可能地定位提供定量依据。
基于以上描述，在一种实施方式中，图1所述实施例中的步骤S30可以按照如下技术手段实施：
利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在的位置概率分布满足二维正态分布的概率模型；利用所述概率模型，按照预设时间间隔△T，获取工作场地中每个位置点有工人存在的工人分布概率，并以等高线的形式生成可视化的所述实时概率图。
本发明实施例中，假设工作场地内工人移动方向随机的情况下，利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型可以表示为数学表达式（1）：
所述数学表达式（1）中，（x，y）服从参数μ1、μ2、s1、s2和ρ的二维正态分布；其中，所述参数μ1、μ2、s1、s2和ρ均为常数，其取值范围分别为：σ1≥0；σ2≥0；-1<ρ<1；-∞<μ1<+∞；-∞<μ2<+∞。
在假设工人移动方向随机的情况下，利用概率时间地理在定位技术上的应用原理，工人以最大步行速度V在单位时间T内所能到达的平面区域可以用圆形表示，也称为潜在区域（potential
path area，PPA）。在单位时间T内的任意时刻，工人所在的位置概率分布符合二维正态分布的概率模型，即数学表达式（1）对应的概率模型。其中μ1、μ2、s1、s2和ρ都是常数，称（x，y）服从参数μ1、μ2、s1、s2和ρ的二维正态分布。μ1、μ2、s1、s2和ρ的取值范围分别为：σ1≥0；σ2≥0；-1<ρ<1；-∞<μ1<+∞；-∞<μ2<+∞。如图2所示，图2是本发明工人位置估算方法中工人所在位置概率分布对应的一种实施方式的概率模型示意图；所述概率模型对应的数学表达式（1）的函数在三维空间中的图像，是一个椭圆切面的钟倒扣在平面上，即图2所示。其中，所述概率模型中的正态分布的参数s1、s2与工人的步行速度成正比，即工人步行速度越大，所述概率模型中的正态分布对应的方差越大。
基于数学表达式（1）对应的概率模型和图2所示的三维图像，利用所述概率模型，按照预设时间间隔△T，获取工作场地中每个位置点有工人存在的工人分布概率，并以等高线的形式生成可视化的所述实时概率图，可以通过如下技术手段实施：
利用所述概率模型，按照预设时间间隔△T，执行工作场地对应的全局运算，得到所述工作场地中每个位置点有工人存在的工人分布概率；基于所述概率模型，通过将竖直方向的z轴去掉、仅保留x轴和y轴的方式，将所述概率模型对应的三维空间的立体图像转换为二维空间的平面图形，得到一系列包含着圆的、以等高线的形式表示所述工人分布概率的所述实时概率图；其中，所述实时概率图中的每个圆对应的数值即为工人出现在此处的概率。
在一个实施例中，如图3所示，图3是本发明工人位置估算方法中工人所在位置概率分布对应的一种实施方式的等高线表示的实时概率图；如果对一个二维正态分布的图像比如图2所示的三维图像，将Z轴去掉，以等高线的形式表示工作场地中工人分布的概率值的大小，那么对于D1，D2的图像，就变为了一系列包含着的圆，而每个圆对应的数值即对应工人出现在此处的概率。
基于上述实施例的描述，在本发明的另一个实施例中，假设工作场地内工人移动方向并非随机，则在工人移动方向不随机的情况下，引入麦克斯韦－玻尔兹曼分布律作为所述概率模型的扩充，则在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型演变为：定向移动基于正态分布的概率模型。
本发明实施例中，考虑到工作场地内工人作为自然人的自主性，即工人 移动方向并非随机，也可能会受到其他因素的影响，此种情况下，引入麦克斯韦－玻尔兹曼分布律作为所述概率模型的扩充。由于麦克斯韦－玻尔兹曼分布律对任何物质的微粒（气体、液体、固体的原子和分子、布朗粒子等），在任何保守力场中运动的情形都成立，其中布朗粒子被视为巨大分子。在时间地理中，人一方面具有微粒的扩散特性，如在实际作业中为了避免任务拥挤调配不开，工人倾向于移动到相对宽松的区域待命，这样，人可视为原子、分子和布朗粒子等微粒基于尺度的进一步扩展；另一方面，人的移动也受保守力制约，比如新的机器人呼叫所产生的对工人移动方向的向心力等。基于这种考虑，工人位置的分布实际上演变为定向移动基于正态分布的概率模型。
优选的地，在本发明的一个实施例中，所述机器人调度系统还具备反馈调节的功能。所述工人位置估算方法还包括：
根据生成的以等高线的形式表示的所述实时概率图，反向调控所述工作场地内的机器人集群和/或任务调度。
由于实时概率图直观地展示了各个时刻在工作场地内工人对应的分布概率，因此，通过该等高线的峰点距离和等高线曲线的分布紧密度情况，即可得知不同时刻工作场地内工人的情况。通过对工人分布概率的实时概率图的分析，即可反向调控工作场地内工作的机器人集群和/或进行任务调度。
在一个实施例中，所述机器人调度系统根据生成的以等高线的形式表示的所述实时概率图，反向调控所述工作场地内的机器人集群和/或任务调度，可以按照如下技术手段实施：
根据生成的以等高线的形式表示的所述实时概率图，分析所述实时概率图；若检测到所述实时概率图中各等高线峰点之间的距离低于预设距离，且所述等高线的曲线分布密度大于预设密度，则根据所述等高线的峰点距离和曲线分布密度，重排所述工作场地内的待执行任务，以便分散工人位置；若检测到所述实时概率图中等高线的曲线分布密度低于预设阈值，则根据所述实时概率图，对所述工作场地内的工人进行任务重排。
比如，在具体的应用场景中，所述机器人调度系统根据生成的以等高线的形式表示的所述实时概率图，如果检测到等高线的峰点距离很近（即正态分布曲线的峰点接近），且等高线曲线分布过于紧密（即正态分布的参数s1和s2过小），则说明工作场地中目前的任务过于集中在某处。在反向调节时，可以依据峰点距离和曲线密度设置适当阈值，比如，针对峰点距离设置对应的所述预设距离，针对等高线的曲线密度设置对应的所述预设密度，当分别达到阈值时，比如等高线的各峰点之间的距离低于预设距离，和/或：等高线各曲线之间对应的曲线分布密度达到预设密度时，所述机器人调度系统开始执行反向调控，重排机器人集群的调度安排，比如采取分散任务、分散工人位置等措施。
所述机器人调度系统如果检测到等高线曲线分布过于松散（即正态分布的参数s1和s2过大），比如上述各等高线曲线之间的曲线密度低于预设阈值，则说明当前工作场地中目前可执行的任务较少。此时，所述机器人调度系统开始执行反向调控，根据所述实时概率图，对所述工作场地内的工人进行任务重排；比如，设置工人轮休时间，让部分工人轮流离岗休息；或者是，调小工人的行进速度V，以降低参数s1和s2。本发明实施例中，针对调小工人的行进速度V，在具体应用时，可以根据具体需求选择不同的实现方式。由于工人是自然人，因此可以通过语音信息的方式提醒用户，或者，通过调度机器人前往不同距离的位置处执行相关任务等方式均可，只要达到对应的目的即可。另外，本发明实施例主要阐述的是本发明的发明构思和思想，至于具体的实时方式，可以根据不同应用场景、不同工作场地进行具体的设置和配置，本发明实施例不进行一一穷举和赘述。
本发明实施例的工人位置估算方法，达到了在不改变现有场地环境以及工人不佩戴任何定位设备的前提下、实时估算工人的位置分布概率的目的，充分利用了资源，达到了高效、低成本地实现人机交互的有益效果，同时也提高了人机的协同性。
基于上述实施例的描述，如图4所示，图4是本发明工人位置估算方法中应用场景的一种实施方式的工作场景信号流示意图。图4所述的工作场景基于本发明描述的工人位置估算方法的思想运行，在图4所述的应用场景中，本发明工人位置估算方法对应的系统运行环境是以流计算模型为基础的处理系统；其主要工作是，将机器人与工人之间的交互信息中的位置信息作为流入口，通过利用工人位置估算方法，实时产生工人位置对应的概率分布；进而以工人位置概率分布对应的实时概率图作为基础，进行机器人集群和/或任务调度。
在图4对应的工作场景中，利用机器人原有的定位模块和所述机器人调度系统原有的系统进程，没有改动仓储的硬件布局，也无需给工人增加额外的定位设备，充分利用现有的机器人调度系统和机器人之间的通信数据即可实现本发明工人位置估算方法、设备及存储介质对应的密度。这是由于机器人与机器人调度系统之间的通信数据中包含了人机交互的位置信息，即在某时刻一名工人与机器人协作时这名工人出现的位置，所以机器人调度系统实际上在通过机器人源源不断地接收工人出现的位置这一数据，本发明的主要思想是：将机器人调度系统通过机器人源源不断地获取到的工人出现的位置这一数据进行充分地利用，并利用本发明工人位置估算方法、设备及存储介质对应的适合具体应用场景的算法，计算得到工人分布概率。
进一步地，该机器人调度系统也可以基于得到的实时的工人分布概率，反向调节，进行工作场地的优化调度，比如安排新的作业，从而产生新的人机交互，并产生新的数据流；如此，并可进入正向的数据循环和机器人调度系统的不断运行。
图4所述的应用场景中的机器人调度系统利用已有的人机交互信号，通过本发明工人位置估算方法、设备及存储介质对应的适合具体场景的算法，使用流计算框架，实时估算出工人位置分布，且基于此，调控机器人集群和/或任务调度，达到了高效、低成本地实现机器人与工人合作场景下工人定位的目的，提高了机器人和工人之间的协同性。
基于上述实施例的描述，对应于上述实施提供的一种工人位置估算方法，如图5所示，本发明实施例还提供了一种工人位置估算装置，包括：
位置获取模块100，设置为：在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；
概率图生成模块200，设置为：基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；
工人位置估算模块300，设置为：基于生成的所述实时概率图，估算工作场地中工人的实时位置。
在一个实施例中，所述工人位置估算装置还设置为：
以通过所述实时概率图估算得到的工人的实时位置为基础，优化任务调度算法，调度机器人前往所述实时概率图对应的最优任务范围，并在机器人与工人完成交互作业时，接收机器人传回的机器人实时位置信息；以便根据机器人传回的所述机器人实时位置信息，获取对应的工人分布概率，更新所述实时概率图。
在一个实施例中，所述概率图生成模块200设置为：利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在的位置概率分布满足二维正态分布的概率模型；利用所述概率模型，按照预设时间间隔△T，获取工作场地中每个位置点有工人存在的工人分布概率，并以等高线的形式生成可视化的所述实时概率图。
在一个实施例中，所述概率图生成模块200设置为：在工人移动方向随机的情况下，利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型可以表示为数学表达式（1）：
所述数学表达式（1）中，（x，y）服从参数μ1、μ2、s1、s2和ρ的二维正态分布；其中，所述参数μ1、μ2、s1、s2和ρ均为常数，其取值范围分别为：σ1≥0；σ2≥0；-1<ρ<1；-∞<μ1<+∞；-∞<μ2<+∞。
在一个实施例中，所述概率图生成模块200设置为：利用所述概率模型，按照预设时间间隔△T，执行工作场地对应的全局运算，得到所述工作场地中每个位置点有工人存在的工人分布概率；基于所述概率模型，通过将竖直方向的z轴去掉、仅保留x轴和y轴的方式，将所述概率模型对应的三维空间的立体图像转换为二维空间的平面图形，得到一系列包含着圆的、以等高线的形式表示所述工人分布概率的所述实时概率图；其中，所述实时概率图中的每个圆对应的数值即为工人出现在此处的概率。
在一个实施例中，所述概率图生成模块200设置为：在工人移动方向并非随机的情况下，引入麦克斯韦－玻尔兹曼分布律作为所述概率模型的扩充，则在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型演变为：定向移动基于正态分布的概率模型。
在一个实施例中，所述工人位置估算装置设置为：根据生成的以等高线的形式表示的所述实时概率图，反向调控所述工作场地内的机器人集群和/或任务调度。
在一个实施例中，所述工人位置估算装置设置为：根据生成的以等高线的形式表示的所述实时概率图，分析所述实时概率图；若检测到所述实时概率图中各等高线峰点之间的距离低于预设距离，和/或所述等高线的曲线分布密度达到预设密度，则根据所述等高线的峰点距离和曲线分布密度，重排所述工作场地内的待执行任务，以便分散工人位置；若检测到所述实时概率图中等高线的曲线分布密度低于预设阈值，则根据所述实时概率图，对所述工作场地内的工人进行任务重排。
本发明工人位置估算装置具备上述实施例中所述机器人调度系统的全部功能，且具体实施方式与上述工人位置估算方法对应的各实施例的实施原理基本相同，在此不作累述。
本发明工人位置估算装置，达到了在不改变现有场地环境以及工人不佩戴任何定位设备的前提下、实时估算工人的位置分布概率的目的，充分利用了资源，达到了高效、低成本地实现人机交互的有益效果，同时也提高了人机的协同性。
本发明还提供了一种电子设备，所述电子设备可以按照图1所述的工人位置估算来估算工作场地中工人的实时位置。如图6所示，图6是本发明电子设备的一种实施方式的内部结构示意图。图6所示的电子设备，在不改变现有场地环境以及工人不佩戴任何定位设备的前提下，能够实时估算工人的位置分布概率，高效、低成本地实现工人与机器人集群合作场景下的工人定位。
在本实施例中，电子设备1可以是PC（Personal Computer，个人电脑），也可以是智能手机、平板电脑、便携计算机等终端设备。该电子设备1至少包括存储器11、处理器12，通信总线13，以及网络接口14。
其中，存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、磁性存储器、磁盘、光盘等。存储器11在一些实施例中可以是电子设备1的内部存储单元，例如该电子设备1的硬盘。存储器11在另一些实施例中也可以是电子设备1的外部存储设备，例如电子设备1上配备的插接式硬盘，智能存储卡（Smart
Media Card, SMC），安全数字（Secure Digital,
SD）卡，闪存卡（Flash Card）等。进一步地，存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据，例如工人位置估算程序01的代码等，还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器（Central
Processing Unit, CPU）、控制器、微控制器、微处理器或其他数据处理芯片，用于运行存储器11中存储的程序代码或处理数据，例如执行工人位置估算程序01等。
通信总线13用于实现这些组件之间的连接通信。
网络接口14可选的可以包括标准的有线接口、无线接口（如WI-FI接口），通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地，该电子设备1还可以包括用户接口，用户接口可以包括显示器（Display）、输入单元比如键盘（Keyboard），可选的用户接口还可以包括标准的有线接口、无线接口。可选地，在一些实施例中，显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED（Organic
Light-Emitting Diode，有机发光二极管）触摸器等。其中，显示器也可以适当的称为显示屏或显示单元，用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
图6仅示出了具有组件11-14以及工人位置估算程序01的电子设备1，本领域技术人员可以理解的是，图6示出的结构并不构成对电子设备1的限定，可以包括比图示更少或者更多的部件，或者组合某些部件，或者不同的部件布置。
基于上述实施例的描述，在图6所示的电子设备1实施例中，存储器11中存储有工人位置估算程序01；所述存储器11上存储的工人位置估算程序01可在所述处理器12上运行，所述工人位置估算程序01被所述处理器12运行时实现上述工人位置估算方法的步骤。：
本发明实施例的电子设备具体实施方式与上述工人位置估算方法对应的各实施例的实施原理基本相同，上述各方法实施例的技术特征在本实施例中均能对应适用，在此不作累述。
此外，本发明实施例还提供了一种计算机存储介质，所述计算机存储介质上存储有工人位置估算程序，所述工人位置估算程序可以被一个或者多个处理器执行，以实现上述工人位置估算方法的步骤。
需要说明的是，本发明实施例的计算机可读存储介质具体实施方式与上述工人位置估算方法对应的各实施例的实施原理基本相同，上述各方法实施例的技术特征在本实施例中均能对应适用，在此不作累述。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。
本发明提供的工人位置估算方法、设备及存储介质，通过在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；基于生成的所述实时概率图，估算工作场地中工人的实时位置；达到了在不改变现有场地环境以及工人不佩戴任何定位设备的前提下、实时估算工人的位置分布概率的目的，充分利用了资源，达到了高效、低成本地实现人机交互的有益效果，同时也提高了人机的协同性。因此，具有工业实用性。
Claims (11)
- 一种工人位置估算方法，包括：在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；基于生成的所述实时概率图，估算工作场地中工人的实时位置。
- 如权利要求1所述的工人位置估算方法，其中，所述基于生成的所述实时概率图，估算工作场地中工人的实时位置之后，还包括：以通过所述实时概率图估算得到的工人的实时位置为基础，优化任务调度算法，调度机器人前往所述实时概率图对应的最优任务范围，并在机器人与工人完成交互作业时，接收机器人传回的机器人实时位置信息；以便根据机器人传回的所述机器人实时位置信息，获取对应的工人分布概率，更新所述实时概率图。
- 如权利要求1或2所述的工人位置估算方法，其中，所述基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图，包括：利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在的位置概率分布满足二维正态分布的概率模型；利用所述概率模型，按照预设时间间隔△T，获取工作场地中每个位置点有工人存在的工人分布概率，并以等高线的形式生成可视化的所述实时概率图。
- 如权利要求3所述的工人位置估算方法，其中，所述利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在的位置概率分布满足二维正态分布的概率模型，包括：在工人移动方向随机的情况下，利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型可以表示为数学表达式（1）：
所述数学表达式（1）中，（x，y）服从参数μ1、μ2、s1、s2和ρ的二维正态分布；其中，所述参数μ1、μ2、s1、s2和ρ均为常数，其取值范围分别为：σ1≥0；σ2≥0；-1<ρ<1；-∞<μ1<+∞；-∞<μ2<+∞。 - 如权利要求4所述的工人位置估算方法，其中，所述利用所述概率模型，按照预设时间间隔△T，获取工作场地中每个位置点有工人存在的工人分布概率，并以等高线的形式生成可视化的所述实时概率图，包括：利用所述概率模型，按照预设时间间隔△T，执行工作场地对应的全局运算，得到所述工作场地中每个位置点有工人存在的工人分布概率；基于所述概率模型，通过将竖直方向的z轴去掉、仅保留x轴和y轴的方式，将所述概率模型对应的三维空间的立体图像转换为二维空间的平面图形，得到一系列包含着圆的、以等高线的形式表示所述工人分布概率的所述实时概率图；其中，所述实时概率图中的每个圆对应的数值即为工人出现在此处的概率。
- 如权利要求4所述的工人位置估算方法，其中，所述利用概率时间地理在定位技术上的应用原理，在单位时间T内的任意时刻，工人所在的位置概率分布满足二维正态分布的概率模型，包括：在工人移动方向并非随机的情况下，引入麦克斯韦－玻尔兹曼分布律作为所述概率模型的扩充，则在单位时间T内的任意时刻，工人所在位置概率分布对应的所述概率模型演变为：定向移动基于正态分布的概率模型。
- 如权利要求3所述的工人位置估算方法，其中，所述工人位置估算方法还包括：根据生成的以等高线的形式表示的所述实时概率图，反向调控所述工作场地内的机器人集群和/或任务调度。
- 如权利要求7所述的工人位置估算方法，其中，所述根据生成的以等高线的形式表示的所述实时概率图，反向调控所述工作场地内的机器人集群和/或任务调度，包括：根据生成的以等高线的形式表示的所述实时概率图，分析所述实时概率图；若检测到所述实时概率图中各等高线峰点之间的距离低于预设距离，和/或所述等高线的曲线分布密度达到预设密度，则根据所述等高线的峰点距离和曲线分布密度，重排所述工作场地内的待执行任务，以便分散工人位置；若检测到所述实时概率图中等高线的曲线分布密度低于预设阈值，则根据所述实时概率图，对所述工作场地内的工人进行任务重排。
- 一种工人位置估算装置，包括位置获取模块、概率图生成模块以及工人位置估算模块，其中：所述位置获取模块设置为：在每个工作阶段的初始时，获取工人预先进入指定位置点所对应的工人初始位置；实时监控机器人与工人之间的人机交互事件，获取机器人的实时位置信息；所述概率图生成模块设置为：基于获取的所述工人初始位置和机器人的所述实时位置信息，按照预设时间间隔，获取工作场地中每个位置点有工人存在的工人分布概率，生成所述工人分布概率对应的可视化的实时概率图；所述工人位置估算模块设置为：基于生成的所述实时概率图，估算工作场地中工人的实时位置。
- 一种电子设备，包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的工人位置估算程序，所述工人位置估算程序被所述处理器运行时，执行如权利要求1至7中任一项所述的工人位置估算方法。
- 一种计算机可读存储介质，所述存储介质上存储有工人位置估算程序，所述工人位置估算程序可以被一个或者多个处理器执行，以实现如权利要求1至7中任一项所述的工人位置估算方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010660522.XA CN111552260B (zh) | 2020-07-10 | 2020-07-10 | 工人位置估算方法、设备及存储介质 |
| CN202010660522.X | 2020-07-10 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022007754A1 true WO2022007754A1 (zh) | 2022-01-13 |
Family
ID=72005374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/104570 WO2022007754A1 (zh) | 2020-07-10 | 2021-07-05 | 工人位置估算方法、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111552260B (zh) |
| WO (1) | WO2022007754A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116680545A (zh) * | 2023-08-02 | 2023-09-01 | 西安核音智言科技有限公司 | 一种基于马尔科夫随机场的煤矿出井人员预测方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111552260B (zh) * | 2020-07-10 | 2020-10-27 | 炬星科技（深圳）有限公司 | 工人位置估算方法、设备及存储介质 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107414822A (zh) * | 2016-05-23 | 2017-12-01 | 富士施乐株式会社 | 机器人控制系统和机器人控制方法 |
| CN109579849A (zh) * | 2019-01-14 | 2019-04-05 | 浙江大华技术股份有限公司 | 机器人定位方法、装置和机器人及计算机存储介质 |
| WO2019151139A1 (ja) * | 2018-01-30 | 2019-08-08 | 株式会社日立製作所 | 作業者モニタリングシステム、それに用いる作業者端末、及び、ビーコンの配置方法 |
| CN110942474A (zh) * | 2019-11-27 | 2020-03-31 | 炬星科技（深圳）有限公司 | 机器人目标跟踪方法、设备及存储介质 |
| CN111340286A (zh) * | 2020-02-24 | 2020-06-26 | 广东博智林机器人有限公司 | 机器人调度方法、装置、电子设备以及存储介质 |
| CN111552260A (zh) * | 2020-07-10 | 2020-08-18 | 炬星科技（深圳）有限公司 | 工人位置估算方法、设备及存储介质 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4550882B2 (ja) * | 2004-11-25 | 2010-09-22 | シャープ株式会社 | 情報分類装置、情報分類方法、情報分類プログラム、情報分類システム |
| CN105425759A (zh) * | 2015-12-30 | 2016-03-23 | 毛扬 | 智能工地管理系统及方法 |
| CN107103388B (zh) * | 2017-04-26 | 2021-02-05 | 杨毅 | 基于需求预测的机器人调度系统与方法 |
| AU2019369396A1 (en) * | 2018-10-29 | 2021-05-27 | Strong Force TX Portfolio 2018, LLC | Adaptive intelligence and shared infrastructure lending transaction enablement platform |
| CN110135744B (zh) * | 2019-05-21 | 2021-04-16 | 郑州航空工业管理学院 | 建筑工人安全行为习惯评价方法 |
| CN111080260A (zh) * | 2019-12-19 | 2020-04-28 | 巢湖学院 | 一种智慧工地管理平台 |
-
2020
- 2020-07-10 CN CN202010660522.XA patent/CN111552260B/zh active Active
-
2021
- 2021-07-05 WO PCT/CN2021/104570 patent/WO2022007754A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107414822A (zh) * | 2016-05-23 | 2017-12-01 | 富士施乐株式会社 | 机器人控制系统和机器人控制方法 |
| WO2019151139A1 (ja) * | 2018-01-30 | 2019-08-08 | 株式会社日立製作所 | 作業者モニタリングシステム、それに用いる作業者端末、及び、ビーコンの配置方法 |
| CN109579849A (zh) * | 2019-01-14 | 2019-04-05 | 浙江大华技术股份有限公司 | 机器人定位方法、装置和机器人及计算机存储介质 |
| CN110942474A (zh) * | 2019-11-27 | 2020-03-31 | 炬星科技（深圳）有限公司 | 机器人目标跟踪方法、设备及存储介质 |
| CN111340286A (zh) * | 2020-02-24 | 2020-06-26 | 广东博智林机器人有限公司 | 机器人调度方法、装置、电子设备以及存储介质 |
| CN111552260A (zh) * | 2020-07-10 | 2020-08-18 | 炬星科技（深圳）有限公司 | 工人位置估算方法、设备及存储介质 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116680545A (zh) * | 2023-08-02 | 2023-09-01 | 西安核音智言科技有限公司 | 一种基于马尔科夫随机场的煤矿出井人员预测方法 |
| CN116680545B (zh) * | 2023-08-02 | 2023-10-20 | 西安核音智言科技有限公司 | 一种基于马尔科夫随机场的煤矿出井人员预测方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111552260B (zh) | 2020-10-27 |
| CN111552260A (zh) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022007754A1 (zh) | 工人位置估算方法、设备及存储介质 | |
| US9946563B2 (en) | Batch scheduler management of virtual machines | |
| CN103092316B (zh) | 一种基于数据挖掘的服务器功耗管理系统 | |
| US11900708B2 (en) | Neural network-based recognition of trade workers present on industrial sites | |
| EP3248736B1 (en) | Control system for controlling a plurality of robots according to their use probability | |
| CN103970264B (zh) | 手势辨识与控制方法及其装置 | |
| US11809678B2 (en) | Three dimensional visual programming interface for a network of devices | |
| CN104303156A (zh) | 监测移动多处理器平台中的行为特征 | |
| CN103399543A (zh) | 输片协作的多个机器人设备的调度方法及系统 | |
| US9104491B2 (en) | Batch scheduler management of speculative and non-speculative tasks based on conditions of tasks and compute resources | |
| US10573273B2 (en) | Method and system for device placement based optimization techniques | |
| JP6948420B2 (ja) | インタラクション方法、機器、システム、電子機器及び記憶媒体 | |
| WO2021258023A1 (en) | Robotic intervention systems | |
| JP6651086B1 (ja) | 画像分析プログラム、情報処理端末、及び画像分析システム | |
| WO2021248857A1 (zh) | 一种障碍物属性判别方法、系统及智能机器人 | |
| US20240004706A1 (en) | Methods and systems for scheduling energy-efficient execution of periodic, real-time, directed-acyclic-graph tasks | |
| CN106293674B (zh) | 自动增减数据消费者的方法以及使用该方法的装置 | |
| CN107291597A (zh) | 一种基于多核异构处理器的运维多模态决策感知系统 | |
| Choi et al. | Scout: Data center monitoring system with multiple mobile robots | |
| CN111047716B (zh) | 三维场景的态势标绘方法、计算机存储介质及电子设备 | |
| JP2002157079A (ja) | 意向識別方法 | |
| CN111930240A (zh) | 基于ar交互的运动视频采集方法、装置、电子设备及介质 | |
| Shruti et al. | Arduino Based Hand Gesture Controlled Robot | |
| KR20200063673A (ko) | 복수의 태스크들을 스케줄링하는 전자 장치 및 그의 동작 방법 | |
| Wang et al. | Multi-agent based modeling and simulation of virtual maintenance system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21837944 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21837944 Country of ref document: EP Kind code of ref document: A1 |