• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    The present invention relates to a selective sorting method for identifying and sorting material objects of different natures, sizes and shapes in the form of a cluster, said method being characterized in that the attribution of the nature of the object to be sorted is to capture at least one two-dimensional image in which said object appears, using at least one electromagnetic radiation sensor and to diffuse at least one of said two-dimensional images on a display screen that can be observed by an operator , said operator assigning a nature to said visualized object. The present invention also relates to a device capable of implementing such a method.
    公开号:FR3032366A1
    申请号:FR1551084
    申请日:2015-02-10
    公开日:2016-08-12
    发明作者:Jeremy Doublet；Christophe Gambier；Jean Francois Rezeau；Alexander Mallinson
    申请人:Veolia Environmental SA；
    IPC主号:
    专利说明:

    [0001] TECHNICAL FIELD The present invention relates generally to a selective sorting method for identifying and sorting material objects of different natures, sizes, masses and shapes. The present invention also relates to a device capable of implementing such a sorting method. More specifically, the invention relates to a method for selectively sorting a set of objects in the form of a cluster. The sorting of objects, when done manually, is a physically intense activity, resulting in the repetition at a high rate of relatively large and repetitive gestures, strongly demanding members, especially higher. The repetition of these gestures can be at the origin of 20 musculoskeletal disorders which should be avoided as far as possible in order to minimize any injury or inconvenience caused by this manual sorting. In addition, the manual gripping of objects imposes the presence of operators in the same space as the objects to be sorted, which exposes the operators directly to risks of all types (physical attacks, cuts, bites, soiling, dust, etc. ...) generated by the objects to be sorted. The wearing of personal protective equipment (PPE), as well as the layout of the workstations (ventilation and appropriate infrastructure in particular) are of course likely to reduce these risks, but can not completely remove them. Thus, to reduce the inconvenience caused by manual sorting, and to facilitate the movement of bulky objects and large masses, hydraulic machines can be used in sorting areas. Examples of hydraulic machines include construction machines such as cranes, or hydraulic excavators. On the other hand, these machines do not make it possible to reach satisfactory levels of performance and productivity. In addition, it is difficult to accurately control the extraction of a particular object and to be able to observe it in its entirety during its displacement. For this reason, automated systems are being developed in the industry in order, among other things, to reduce human exposure to dangerous or potentially dangerous situations, to replace manual operations in tedious and repetitive tasks, as well as to increase sorting performance in terms of quality and / or productivity. For example, in the agri-food sector, robotic systems are used to efficiently and quickly sort fruits and vegetables according to various predefined criteria, including physical criteria, such as the shape, size or maturity of a product. organic. On an industrial scale, the current automated sorts do not make it possible to take all of the above-mentioned criteria into consideration simultaneously. Typically, in the field of waste processing, automatic sorting must be coupled with human operations. More precisely, an operator must intervene, often at the end of the chain, to sort each waste 30 since he is the only one capable of recognizing all the objects, whereas the automated sorting machines can only identify a certain number of objects. predefined objects.
    [0002] To this end, great progress has been made on automatic sorting devices, that is to say, automating certain tasks. Automatic sorting devices and the methods of sorting them using them are known to those skilled in the art. For example, the international application WO 98/19799 discloses a method and a device for selective sorting of waste with teleoperator, comprising means for designation on a touch screen of an object to be extracted, and selective extraction means 10 controlled by designation on the touch screen of the object. This designation allows sorting remotely, that is to say that any manual gripping of any object does not require the presence of operator in the same space as the objects.
    [0003] Moreover, more recently, the international application WO 2009/068792 describes a method and a selective sorting device improving those described in WO 98/19799, in particular by allowing a very high rate. More particularly, in the device of WO 2009/068792, it is possible to modify the visual appearance of an image of a targeted object on a video screen. However, it should be noted that these devices known from the prior art do not allow the sorting of a cluster that can contain objects of different shapes and / or different sizes and / or different nature. Indeed, these devices only allow the sorting of objects previously presented in unitary form. More generally, it is known to those skilled in the art automated sorting devices for sorting objects of different natures, masses or shapes such as waste, only if these objects are previously in unitary form. In this configuration, all the objects are separated from each other, so that it is possible to distinguish their outline and the objects that remain in the form of clusters are sorted manually at the end of the sorting chain. DESCRIPTION OF THE INVENTION Thus, there is therefore a real need to provide a method and a device that makes it possible to sort a cluster that can contain objects of different sizes and / or shapes and / or natures, particularly waste, in particular. enabling the productivity and efficiency of any sorting process of the prior art to be increased, while decreasing or even eliminating the physical strain of sorting through the use of interfaces rather than contacts between objects and operators.
    [0004] It should be noted that for the purposes of the present invention, clustering is understood to mean a set of heterogeneous objects entangled and arranged randomly on each other, said objects being waste. In this context, the Applicant has developed a method which overcomes the disadvantages of the prior art and meets the objectives cited above. More particularly, the present invention relates to a selective sorting method for identifying and sorting material objects of different types, sizes, and shapes and in the form of a cluster, said method comprising the following steps: a) supplying a flow of objects in the form of a cluster, to a vision zone comprising at least two electromagnetic radiation measuring sensors, said zone being in the action zone of a robot provided with a or more gripping organs; b) capturing at least two two-dimensional images of the cluster contained in said viewing zone using said electromagnetic radiation measuring sensors, to reconstruct a virtual or electronic image of the cluster of objects in the area of vision that can be viewed on a screen; c) processing the information resulting from said two-dimensional images, and identifying all possible gripping areas associated with objects present in the cluster for said gripping member (s) of said robot, without seeking to know the nature of said objects; D) locating, in position and orientation, said possible gripping zones, and e) selecting one of the gripping zones; f) automatically defining, for a given gripping member, a gripping trajectory of an object corresponding to the chosen gripping zone; g) enter the corresponding unit object according to the defined trajectory; h) moving said seized unit object to a receiving area; I) moving said unitary object in said receiving area to an outlet depending on the nature; said method being characterized in that the nature of the object grasped or to be grasped by the robot is defined and assigned between steps e) and i), and consists in capturing at least one two-dimensional image in which said object appears, using at least one two-dimensional image sensor and broadcasting at least one of said two-dimensional images on a viewing screen that can be observed by an operator, said operator assigning a nature to said visualized object. It should be noted that the cluster of objects that can be sorted by the method according to the invention may for example contain, without limitation, bulky objects or objects of small size, any waste whatsoever , industrial or domestic. For the purposes of the invention, the term "waste" is understood to mean any object, or more generally any movable good, the holder of which is undone or whose intention or obligation it is to dispose of, for the purposes of recovery. or disposal, whether the holder is an industrialist, a community or an individual. The objects of the cluster that can be sorted by the process 10 according to the invention are, for example, organic or non-organic household waste, electronic waste, construction-related waste, furniture waste, industrial waste. etc. In general, objects that are to be sorted are conveyed to a processing center for recovery, for example for recycling. It should be noted that the objects to be sorted are typically arranged in the form of bulk or clusters, which may comprise a greater or lesser number of random entangled objects, in a particular and predefined area of the processing center. Then, they are usually transferred to processing means and other specific devices. Their transfer from a particular and predefined area of the treatment center to treatment means is achieved by using known transfer means, for example shovels or conveyors. The method according to the invention is thus fed by these object transfer means to be sorted, said objects to be sorted generally being in the form of clusters.
    [0005] Then, the method according to the invention is implemented to identify and sort a succession of clusters consisting of material objects of different natures, shapes and sizes. The first step a) of the method according to the invention consists in supplying a viewing zone with objects generally in the form of clusters, the viewing zone being in the zone of action of a robot provided with one or more gripping members. The zone of vision of the method according to the invention can be confused with the aforementioned particular and predefined zone of the processing center, the objects to be sorted being, for example, directly discharged into this zone of vision by a collecting vehicle. The supply of this zone of vision into objects can be carried out either according to a batch supply or according to a continuous supply. For the purposes of the present application, batch feed means a batch feed. In other words, the feeding of the viewing zone is discontinuous. Only one cluster of objects at a time is processed. In this configuration, until all the objects have been sorted, the viewing area is not powered. But when the last object to be valorised previously contained in the cluster is grasped by at least one gripping member of said robot, another cluster is moved in the viewing zone to be sorted later. For the purposes of the present application, the term "continuous supply" means a power supply without deactivation of the means making it possible to supply the vision zone with objects. In this configuration, objects to be sorted are moved to the continuous viewing area. This zone of vision comprises at least two sensors for measuring electromagnetic radiation. It is also possible to add in this zone a source of incident electromagnetic radiation in order to allow sufficient level of electromagnetic radiation emission by the cluster of objects to capture images representative of the actual cluster. In the present application, the electromagnetic radiation measuring sensors are used to identify the nature of the unitary object located in said receiving zone. It should be noted that these electromagnetic radiation measuring sensors can be directly attached to the articulated mechanical arm of the robot. In this configuration, the one or more image captures, made by the electromagnetic radiation measuring sensors, are performed when the unitary object is under the influence of one of the gripping members of the robot. In other words, the assignment of a nature to the unitary object is made as it moves between the viewing area and the receiving area. During this identification, it is therefore not necessary for the unitary object to be deposited in a particular area. Within the meaning of the present application, unitary object is understood to mean any object initially contained previously in the cluster of objects to be sorted and which has been extracted therefrom. The measurements made by these electromagnetic radiation sensors make it possible, in step b) of the method according to the invention, to produce at least two two-dimensional images of the cluster present in said zone of vision. These two-dimensional images make it possible to reconstruct one or more virtual or electronic images of the cluster of objects in the zone of vision that can be viewed on a screen.
    [0006] Transformation of electromagnetic radiation measurements into two-dimensional image is made possible by the use of computational software. These two-dimensional images are analyzed and processed, step c) of the method according to the invention, in order to identify all the possible gripping zones for the gripping member (s) of the robot and to identify the gripping member on the more adapted for each of the possible catch areas, said zones being associated with objects present in the cluster.
    [0007] It should be noted that for each capture zone, or specific zone, is meant within the meaning of the present invention, an area that can be grasped by any gripping member of a robot. It should also be noted that several capture areas may be associated with an object contained in the cluster. The processing of these two-dimensional images can, for example, be done using computational software and image processing software. After all the tap areas have been identified by the two-dimensional image processing and analysis, the tap areas are located in position and orientation, step d) of the method according to the invention. Then, according to the method of the invention, the nature of the object grasped or to be grasped by the robot is assigned between steps e) and i), and consists in capturing at least one two-dimensional image using at least one two-dimensional image sensor and diffusing at least two-dimensional images on a display screen observable by an operator, the operator assigning a nature to a unitary object displayed. According to a first advantageous embodiment of the method of the invention, the step of defining the nature of the unitary object grasped is carried out in the receiving zone, and more particularly between the steps h) and i) mentioned above. . According to this first embodiment, the choice of one of the gripping zones, step e) of the method according to the invention, can advantageously be carried out automatically by virtue of the use of an algorithm. Advantageously, the selection of a specific area is performed through the use of a controller, which does not require the intervention of an operator.
    [0008] It should be noted that during this input, the robot's trajectory can be calculated by the use of computational software. In addition, a particular capture path may be associated with each tap area. The method is then advantageous because it is possible to quickly enter and deposit a unitary object. After the robot has grasped the gripping zone defined by the algorithm with one of its gripping members, the unitary object associated with that gripping zone is transferred from the viewing zone to a zone. reception. According to this first embodiment, the step of defining the nature of the object in the reception area can be advantageously achieved by capturing at least one two-dimensional image of the unitary object in the reception area at the reception area. using at least one electromagnetic radiation measuring sensor and to broadcast at least one of these two-dimensional images of the unitary object on a viewing screen that can be observed by an operator, who in real time attributes a nature to the unitary object viewed in the receiving area. In this embodiment, the intervention of an operator is necessary. It should be noted that the various electromagnetic radiation measuring sensors mentioned above are chosen as a function of the source or sources of electromagnetic radiation used. After the assignment of a particular nature to an object present in the reception area, the same object is moved from the reception area to an outlet according to the nature assigned to it beforehand.
    [0009] According to a second advantageous embodiment of the method of the invention, the step of defining the nature of the object seized or to be grasped can be carried out between the steps e) and f) mentioned above, starting from virtual image of the cluster of objects of step b), which is broadcast on at least one viewing screen that can be observed by an operator, said operator assigning a nature to said object to be grasped within the cluster of objects visualized.
    [0010] 5 A nature is attributed to an object in the cluster when it is in the vision zone. In this embodiment, the intervention of an operator is then necessary. Advantageously, in a first step, one of the capture zones may be targeted by an operator on the viewing screen broadcasting said virtual image representing the cluster located in the viewing zone. Then, in a second step, advantageously, the operator can assign a nature to the preselected gripping area, corresponding to a particular object, interactively through the use of touch screen video, or a video screen associated with a voice recognition system or a keyboard-like system or any other system allowing the particular selection of a specific area.
    [0011] According to this second advantageous embodiment of the method of the invention, after having attributed a particular nature to a preselected gripping zone by an operator, any of the gripping members of a robot can enter this preselected gripping zone. to move the object from the viewing area to the receiving area. As for the first embodiment of the invention, it should be noted that during the capture, the robot's take-off trajectory can be advantageously calculated by the use of computational software. In addition, a particular input path may be associated with each tap area. The method is advantageous because it is possible to quickly grab and deposit objects.
    [0012] After the robot has grasped said preselected zone by an operator by one of its gripping members, the unitary object, associated with this preselected gripping zone, is transferred from the viewing zone to a receiving zone.
    [0013] In the context of the second embodiment of the method according to the invention, an operator having previously assigned a nature to the object in the receiving area, the object can be advantageously moved from the reception area to a reception area. predefined outlet according to this nature. It should be noted that whatever the embodiment according to the invention, the viewing zones of the cluster of objects and the receiving zone of the unitary object are distinct zones, that is to say separate processing center volumes. It should be noted that according to the first advantageous mode of the invention, the totality of the objects contained in the initial cluster is sorted, that is to say that all the objects are grasped by the robot and transits from the zone. from vision to the receiving area. And according to the second advantageous mode of the invention, all the objects contained in the initial cluster is not necessarily sorted and therefore does not necessarily pass from the viewing area to the receiving area.
    [0014] In this case, an outlet intended to receive the objects not grasped by any gripping member may be placed close to the viewing zone in order to allow its evacuation. In other words, all the objects not grasped by any of the gripping members of the robot 30 are moved to a particular outlet by the use of any transfer means. The present invention also relates to a selective sorting device, capable of implementing the method described above, and comprising: - means for providing a flow of objects in the form of a cluster; electromagnetic radiation measuring sensors for making one or more two-dimensional images; image processing and calculation software for processing the resulting information of said captured images and for identifying and locating gripping areas of the objects of the cluster; A mechanical robot provided with at least one gripping member for grasping an object defined by one or more gripping zones in the cluster and moving it from a viewing zone to a receiving zone; means for evacuating the object placed in the reception zone; means for broadcasting at least one of said two-dimensional images on at least one viewing screen that can be observed by an operator, so that said operator can attribute a nature to said object being viewed. The device according to the invention is advantageous because it allows sorting remotely avoiding contact between an operator and any object to be sorted. In this regard, interfaces may be used to allow an operator to control and control the remote sorting device. In addition, the device according to the invention makes it possible to sort clusters of objects containing multiple material objects, including waste, which may be of different natures, sizes and shapes.
    [0015] The device according to the invention comprises means for providing a flow of objects in the form of clusters. For example, these means may be belt conveyors or roller conveyors, roller conveyors, ball tables, vibrating tables, mechanical devices comprising gripping means, or any other device for moving a cluster of dies. object from one initial point to another point. Collection bins in which the objects to be sorted are placed can also be used. In this configuration, the bucket is static during the sorting process and during the gripping of each of the objects it contains. On the other hand, as soon as the objects to be sorted contained in said bucket have been sorted, a bucket containing new objects to be sorted is conveyed into the viewing zone and thus replaces the first bucket. It is also possible that the bucket is directly filled by a collection truck which avoids the replacement of the bucket. The flow of objects feeds an area of the device according to the invention, called vision zone, into a cluster of objects. The device according to the invention further comprises a mechanical robot provided with at least one gripping member making it possible, in a first step, to grip an object contained in the cluster present beforehand in the viewing zone, each object of 20 the cluster being defined by one or more gripping zones, and in a second step of moving the object entered from the viewing zone to another zone, called the receiving zone. It should be noted that after the choice of a particular gripping zone has been carried out, either by an automaton or by an operator, the mechanical robot, by means of at least one of its gripping members , moves the object associated with this particular catch area of the viewing area to the receiving area. The device according to the invention comprises, in particular in the zone of vision, electromagnetic radiation measuring sensors, which can be measurement sensors in the visible or non-visible spectrum, such as gamma radiation sensors, radioelectric sensors. infrared sensors, ultraviolet sensors, X-ray sensors or cameras. Preferably, the electromagnetic radiation measuring sensors are visible spectrum cameras. It should be noted that the aforementioned sensors can also be used in combination. These electromagnetic radiation measurements allow the robot to grab a particular object through a preselected grip area. These electromagnetic radiation measurements may also be analyzed and processed by computational and image processing software to enable the identification and location of all possible capture areas of each object contained in the cluster. For this reason, the electromagnetic radiation measuring sensor (s) may advantageously be connected to image analysis means. It should be noted that an object contained in the cluster may be associated with several gripping zones or specific zones, the computational and image processing software having the objective of identifying gripping surfaces and not objects. Measurements of electromagnetic radiation can allow the development of one or more two-dimensional images.
    [0016] Preferably, the display screen on which one or more of said two-dimensional images are broadcast may be either tactile, associated with a voice recognition system, associated with a keyboard, or associated with a plurality of the aforementioned systems to enable 30 selection of a particular gripping area by an operator. The video screen may furthermore comprise two zones: a first zone which makes it possible to visualize an image coming from the electromagnetic radiation measurement sensors, and thus allow the selection of a particular specific zone, and a second zone of the screen which comprises subcategories respectively corresponding to predetermined natures 5 to allow to assign to the preselected specific area a particular nature. Advantageously, the device may comprise processing and calculation means capable of automatically associating with a gripping surface selected by an operator or an automaton, the most appropriate robot member. In addition, the device may advantageously comprise processing and calculation means capable of automatically defining a gripping trajectory of an object by the specific compatible zone, preselected by an operator or an automaton, for a particular gripping member. a mechanical robot. In this way, the path followed by any gripper of the robot is optimized. It is as fast as possible and as short as possible.
    [0017] Advantageously, the reception zone may comprise one or more sensors for measuring electromagnetic radiation. For the purposes of the present application, the term "receiving zone" is understood to mean a zone whose volume is accessible by a robot 25 as previously described. In this way, the assignment of a nature to an object in the receiving area is performed in this configuration by an operator. For this purpose, the electromagnetic radiation measurement sensors used are sensors making it possible to reproduce one or more virtual or electronic images of the object located in the reception zone. For example, these sensors may be infrared or near-infrared radiation sensors, ultraviolet radiation sensors, X-ray sensors, electromagnetic radiation sensors according to the visible or non-visible spectrum, gamma radiation sensors, Laser scanning distance sensors, and preferably electromagnetic radiation measuring sensors are visible spectrum cameras. The aforementioned sensors can also be used in combination. Preferably, images retrieved by one or more of the aforementioned sensors can be viewed on a touch screen. This touch screen can for example comprise two zones. A first zone can be used to display an image from electromagnetic radiation measuring sensors. A second area of the screen comprises subcategories respectively corresponding to predetermined natures. In this configuration, an operator can assign to the unit object that he displays on said touch screen a particular nature by selecting a particular subcategory.
    [0018] According to another alternative, the video screen is not touch-sensitive, but is associated with a voice recognition system or a keyboard-type system or any other system making it possible to attribute a particular nature to the object displayed on the screen. said screen.
    [0019] After a nature has been assigned to an object placed in the receiving zone, the seized object is evacuated from said receiving area to an outlet, by means of routing according to the nature assigned to it. . These conveying means may be belt conveyors or rollers, roller conveyors, ball tables, vibrating tables, mechanical devices comprising gripping means, or any other device for moving a unitary object d. an initial point to another point. One of the advantageous routing means is the same mechanical robot used to move the cluster object from the viewing area to the receiving area. The object transiting on these conveyance means is moved into a predefined outlet according to the nature that has been assigned to it. For example, the outlets may include manipulator arms or robots adapted to the characteristics of the objects to be extracted. These outlets may also comprise devices for pneumatic ejection conveyor belt jets, compressed air nozzles, referral systems, pushers employing jacks, traps, robots. Extraction means combining different aforementioned ejection devices can be applied. In this way, the path followed by a gripping member of said robot is optimized, typically to be as fast as possible and also as short as possible. In addition, the device according to the invention may comprise means for detecting and tracking the movements and positions of a particular object, between the gripping device of a robot and an outlet, as a function of time. These means may comprise electromagnetic radiation measuring sensors as mentioned above. BRIEF DESCRIPTION OF THE FIGURES Other characteristics and advantages of the present invention will emerge more clearly on reading the following description given by way of illustrative and nonlimiting example and with reference to the appended figures in which: FIG. 1 illustrates an embodiment of a device according to the invention, seen in three-dimensional, able to sort the objects of the cluster automatically selected, according to the first embodiment of the method according to the invention, - Figure 2 illustrates an embodiment of a device according to the invention, seen in three-dimensional, able to sort the objects of the cluster selected by an operator, according to the second embodiment of the method according to the invention, - Figure 3A illustrates a touch screen view that can be viewed by an operator when he assigns a particular nature to an object in unitary form, FIG. 3B illustrates a view of a screen that can be viewed by an operator when the latter selects a particular gripping area and attributes a nature to it. The identical references shown in FIGS. 1 to 3B are identified by identical reference numerals.
    [0020] Embodiments In the examples presented below, by way of indication and without limitation, use is made in the two embodiments of devices according to the invention illustrated in FIGS. 1 and 2, robotic solutions marketed by SILEANE. or by the company AKEO. These devices include a robot which comprises a polyarticulate system provided with one or more grippers capable of grasping an object by a specific area. To facilitate the reading of the figures, a single gripping member is shown in FIGS. 1 and 2. However, preferably, the robot may comprise at least two gripping members, the first using a so-called "suction cup" technology and the another technology called "clamp". This robot is not the one illustrated in the figures. In Figures 1 and 2, the robot comprises a single gripping member using the "clamp" technology.
    [0021] FIG. 1 depicts a device 10 according to the invention, making it possible to extract particular objects contained in a cluster, depending on their nature. The cluster of objects comprises a bulk volume of heterogeneous objects placed randomly so that the objects become entangled. As shown in FIG. 1, the cluster of objects, for processing, is disposed on a first belt conveyor 11.
    [0022] This first conveyor belt 11 is able to supply a zone, called vision zone 12, in a cluster of material objects. This viewing zone 12 is irradiated with electromagnetic radiation from radiation sources in order to produce one or more images of the cluster of objects situated in the viewing zone 12. In addition, the device of FIG. sensors for measuring electromagnetic radiation in order to produce one or more two-dimensional images of the cluster of objects situated in the viewing zone 12.
    [0023] Under these conditions, the electromagnetic radiation measuring sensors are configured to acquire successive two-dimensional images of the cluster located in the viewing zone 12. It should be noted that the captured images cover the entire cluster of objects. .
    [0024] According to the device 10 of FIG. 1, the images are captured by the use of a visible spectrum camera 19a. One or more of said images of the cluster of captured objects are then processed and analyzed to enable identification and location of each possible gripping area by a gripping member 18 of the polyarticulate robot 14. To do this, the electromagnetic radiation measuring sensors are, for example, coupled to processing means, which may be computers and other software, configured to process the images from said sensors. The combined uses of computational software and image processing software make it possible to choose a gripping zone and a gripping member. According to the device 10 of FIG. 1, a gripping member 18 grasps the defined gripping zone. The device of FIG. 1 can furthermore use calculating and image processing software to also make it possible to define the fastest and shortest possible take-off trajectory for a given gripping member 18. It should be noted that in order to obtain images representative of reality, the speed of the flow of objects is directed towards the viewing zone 12, by the use of a belt conveyor 11 according to FIG. , is possibly not constant. For example, when a cluster of objects reaches the viewing area 12, the speed of the flow of objects decreases, or even vanishes, so that the sensors in the viewing area 12 can capture at least two two-dimensional images. representing the cluster of objects. After each capture, the sensors capture new images of the cluster of objects. In this way, the object to be grasped, which could be moved by the input of a previous object, will still be located and seized. On the order of an operator, the first belt conveyor 11 can be put back into operation in order to bring into this viewing zone 12 a new cluster of objects to be sorted. Then, in the device 10 of the invention illustrated in FIG. 1, it is not necessary for the image or images captured by the sensors to be transferred to a video screen since the previously captured images are only useful for identifying and automatically locate each possible gripping zone by a gripping member 18.
    [0025] 3032366 22 It should be noted that here, no operator intervenes. The choice of any one of the gripping zones is carried out automatically according to different pre-established criteria.
    [0026] Then, all the objects contained in the initial cluster are grasped by any gripping member 18, as shown above, is disposed, according to Figure 1, in a receiving zone 13 located on a second belt conveyor 15 .
    [0027] It should be noted that the totality of the objects contained in the initial cluster to be sorted passes from the viewing zone to the reception zone after having been grasped by the robot. According to FIG. 1, each object deposited in this reception zone 13 is assigned a particular nature. This allocation is made through the intervention of an operator who can use an interface. This interface allows the operator to assign a nature to a given object at a given time. The interface is coupled to one or more electromagnetic radiation measuring sensors. According to the device of FIG. 1, the two-dimensional image sensor is a camera 19b operating in the visible spectrum. This camera 19b is connected to a screen and the captured images appear on this screen. These images can be preprocessed by computer to present a certain contrast to the operator and thus give him indications for example on properties or the nature of said object (FIG. 3A). For example, if an object is plastic, a specific color or texture facilitating recognition of the operator can be assigned to said object. This step is particularly interesting for subjects whose effectiveness of recognition does not have good performance.
    [0028] FIG. 3A shows a touch screen 20 that can be viewed by an operator wanting to assign a nature to a unitary object located in the reception zone 13. On this screen, it is possible to display, on the one hand, the object 5 located in the reception area 13, and secondly, to assign a particular nature. To do this, the camera 19b is connected 21 and 22 to: - a touch screen 20, comprising two zones a first area 21 for viewing an image from the camera 19b, and - a second area 22 of the screen, which includes sub-categories 23 respectively corresponding to predetermined natures: for example, a first subcategory 23 corresponds to wood, a second subcategory 23 to scrap, a third subcategory 23 to plastic, a fourth subcategory 23 to engraved. The second screen area may further include a subcategory 23 that does not correspond to any particular nature, but in which an operator can classify all objects regardless of their nature. This subcategory 23 can then complement the other subcategories or be the only one available. In the latter case, possibly, it is possible to have only one outlet 25 16b in which are ejected all objects located on the second conveyor belt 15. It should be noted that the operator who performs the operation Allocation of a nature to a given object must be initiated to this task in order to maintain the flexibility and productivity of the sorting process. According to FIG. 1, after the attribution of a particular nature to an object, the object is directed towards a predefined outlet 16, at first, thanks to the use of a second conveyor 15 and in a second step 3032366 24 through the use of one or more extraction means 17. As shown in Figure 1, the extraction means 17 can extract the objects located on the second 5 conveyor belt 15 and to route them to appropriate outlets for receiving them. Figure 1 shows that these outlets 16 include pneumatic ejection devices using jacks. In addition, means can be used to record and track the movements and positions of a particular object between the gripper 18 of a robot 14 and an outlet 16 as a function of time. Moreover, FIG. 2 describes a device 20 according to the invention making it possible to select in particular one or more objects contained in a cluster, according to the second embodiment of the method according to the invention. The cluster of objects comprises a bulk volume of heterogeneous objects placed randomly so that the objects become entangled. As shown in FIG. 2, the cluster of objects, for the purpose of its treatment, is disposed on a first belt conveyor 11. This first belt conveyor 11 is able to supply a zone, called a vision zone 12. in clusters of material objects. At the level of the viewing zone 12, according to the device 20 of FIG. 2, a visible spectrum camera 19c is used to produce one or more two-dimensional images of the cluster of objects situated in the viewing zone 12. It should be noted that the images captured by the camera 19c cover the entire cluster of objects. According to the device of FIG. 2, the camera 19c is connected to a screen and the captured images appear on this screen. These images may be pre-processed by computer to present a certain contrast to the operator and thus to give him indications as to properties or the nature of said object selected by the designation of a particular gripping zone (FIG. 3B). For example, if an object is plastic, a specific color or texture that facilitates recognition of the operator can be assigned to the object. This step is particularly interesting for materials whose recognition efficiency does not have good performance. In addition, the camera 19c is, for example, coupled to processing means, which may be computers and other software, configured to process the images from the camera 19c and thus to enable the identification and location of all the images. possible catch areas associated with each of the objects in the cluster. The screen on which the images captured by the camera 19c appear is tactile. According to FIG. 3B, the touch screen 20 comprises two zones 21 and 22: a first zone 21 for displaying an image coming from the electromagnetic radiation measuring sensors, and a second zone 22 of the screen, which comprises 25 sub-categories respectively corresponding to predetermined natures: for example, a first subcategory 23 corresponds to wood, a second subcategory 23 to scrap, a third subcategory 23 to plastic, a fourth subcategory - category 23 to engraved. The second screen area may include a sub-category 23 that does not correspond to any particular nature, but in which an operator can classify all the objects selected and previously contained in the cluster. In this last case, possibly, it is possible to have only one outlet 16b in which are ejected all the objects which have been deposited in the reception zone 13 located on the second conveyor belt 15.
    [0029] In FIG. 3B, the possible gripping zones are represented, on the first zone of said touch screen 20, by virtual circles. In this configuration, an operator may designate a finger pointing area on the touch screen 20.
    [0030] According to this configuration, the selection of a gripping area 25 can be corrected. For example, selecting an already selected tap area 25 deselects it. In this configuration, an operator can assign a nature to a given object. It should be noted that the operator who performs the assignment operation of a nature to a given object must be initiated to this task in order to maintain the flexibility and productivity of the sorting process.
    [0031] With this configuration, an operator can, therefore, firstly select a possible pickup area, and in a second step he can assign that particular pickup area a particular nature. The assignment of a nature to a particular pickup zone is as follows. An operator first selects a take zone 25 and then selects a subcategory 23 of allocation. According to this configuration, the selected gripping zone 25 is marked with a graphical sub-referent such as, for example, a colored circle 24.
    [0032] It is also possible to define a mode of operation in unitary category, ie only one category is assigned automatically to all the objects designated by an operator after having selected a possible zone of capture. an object contained in the cluster. In this case the unitary category is previously defined by the operator. It should be noted that the objects not grasped by any gripping member 18 remain in the viewing zone 12, before the first belt conveyor 11 resumes operation. In this way, the objects remaining in this zone of vision 12 are directed towards a common outlet 16a located at the end of the first conveyor belt 11.
    [0033] After the objects have been seized, they are in unitary form in the reception area 13. It should be noted that when the objects are arranged in the reception area 13, to each object has been assigned a nature.
    [0034] As soon as an object is deposited in the reception zone 13, it is moved from this reception zone 13 to a second belt conveyor 15. Indeed, this second belt conveyor 15 being in permanent operation, an object grasps by a gripping member 18 of a robot 14, and then deposited on the second conveyor belt 15, is very quickly set in motion. In this way, each of the objects seized in the initial cluster follows one another throughout this second conveyor belt 15. The second belt conveyor 15 thus makes it possible to extract the unitary object previously deposited in the receiving zone. 13. Since each object has been assigned a nature, each of them can be moved to a specific 16b outlet. According to FIG. 2, the outlet 16b comprises a robot provided with a gripping member capable of grasping any object located on the second conveyor 15 and moving it into a predefined outlet 16b according to the nature which it has been awarded. The robot 14 is used as extraction means 17.
    [0035] Optionally, it is possible to have only one outlet 16b in which all the objects located on the second conveyor belt 15 are ejected. In addition, means can be used to detect and follow the movements and positions of a particular object, between the gripping device 18 of a robot 14 and an outlet 16b, as a function of time. The present invention is not limited to the previously described embodiments.
    权利要求:
    Claims (11)
    [0001]
    REVENDICATIONS1. A method of selective sorting for identifying and sorting waste material objects of different natures, shapes and sizes in the form of a cluster, said method comprising the steps of: a) providing a flow of objects in the form of a cluster, to a viewing zone (12) comprising at least two electromagnetic radiation measuring sensors, said zone being in the zone of action of a robot (14) equipped with one or several gripping organs; b) capturing at least two two-dimensional images of the cluster contained in said viewing zone (12) using said electromagnetic radiation measuring sensors, to reconstruct a virtual or electronic image of the cluster of objects in the viewing area (12) viewable on a screen; c) processing the information resulting from said two-dimensional images, and identifying all possible capture areas associated with objects present in the cluster for said one or more gripping members of said robot (14) without seeking to know the nature of said objects; d) locate, in position and orientation, said possible catch areas; e) choose one of the catch zones; f) automatically defining, for a given gripping member (18), a gripping trajectory of an object corresponding to the chosen gripping zone; G) grasp the corresponding unit object according to the defined trajectory; h) moving said seized unitary object to a receiving area (13); I) moving said unitary object in said receiving area (13) to an outlet (16) depending on the nature; said method being characterized in that the nature of the object grasped or to be grasped by the robot (14) is assigned between steps e) and i), and consists in capturing at least one two-dimensional image in which said object appears , using at least one electromagnetic radiation sensor and diffusing at least one of said two-dimensional images on a display screen observable by an operator, said operator assigning a nature to said object being viewed.
    [0002]
    The selective sorting method according to claim 1, wherein the step of assigning a nature to the seized unit object is performed between step h) and step i) in said receiving area (13). ).
    [0003]
    The selective sorting method according to claim 2, wherein the step of assigning a nature to a unitary object located in the receiving area (13) is performed by capturing, by at least one electromagnetic radiation sensor, at least one two-dimensional image diffused on a viewing screen which can be observed by an operator.
    [0004]
    4. Selective sorting method according to any one of claims 1 to 3, wherein the choice of one of the setting areas of step e) is performed automatically through the use of an algorithm. 3032366 31
    [0005]
    The selective sorting method of claim 1, wherein the step of assigning a nature to the object to be input is performed between step e) and f).
    [0006]
    6. Selective sorting method according to claim 5, wherein the step of assigning a nature to the object to be entered is performed from the virtual or electronic image of the cluster of objects of the step b), which is broadcast on at least one display screen that can be observed by an operator, said operator assigning a nature to said object to be entered within the cluster of objects displayed.
    [0007]
    7. Selective sorting method according to any one of the preceding claims, wherein one of the gripping areas is targeted by an operator on the viewing screen broadcasting said virtual image.
    [0008]
    8. Selective sorting device, capable of implementing the method according to any one of claims 1 to 7, and comprising: - means for providing a flow of objects in the form of a cluster; electromagnetic radiation measuring sensors for producing one or more two-dimensional images; image processing and calculation software for processing the resulting information of said captured images and for identifying and locating gripping areas of the objects of the cluster; a mechanical robot (14) provided with at least one gripping member (18) for grasping an object defined by one or more gripping zones in the cluster and moving it from a viewing zone (12) to a reception area (13); means for evacuating the object placed in the reception zone; means for broadcasting at least one of said two-dimensional images onto at least one viewing screen that can be observed by an operator, so that said operator can attribute a nature to said object being viewed.
    [0009]
    9. Selective sorting device according to claim 8, comprising processing and calculation means for automatically defining a gripping trajectory of said object by said robot (14).
    [0010]
    10. A selective sorting device according to claim 8 or 9, wherein the electromagnetic radiation measuring sensors are measurement sensors in the visible or non-visible spectrum such as gamma radiation sensors, radioelectric sensors. , infrared sensors, ultraviolet sensors, X-ray sensors or cameras. 25
    [0011]
    The selective sorting device according to any one of claims 8 to 10, wherein said video screen is either tactile, or associated with a voice recognition system, or associated with a keyboard, for selecting a particular shooting area, or associated with several of the aforementioned systems.
    类似技术:
    公开号 | 公开日 | 专利标题
    EP3056288B1|2018-03-14|Selective sorting method and device
    EP3056289B1|2018-04-11|Selective sorting method and device
    EP3134234B1|2018-03-21|Method and facility for automatically gripping an object
    EP3256267B1|2019-01-09|Device for separating and individualising postal objects with laser-based vision system
    EP3237123B1|2018-09-26|Device for separating and singulating heterogeneous postal items
    FR2923165A1|2009-05-08|METHOD AND DEVICE FOR SELECTIVE SORTING OF OBJECTS
    US9156064B2|2015-10-13|Apparatus and method for sorting plant material
    WO2011037481A1|2011-03-31|Diamond sorting system
    FR2725640A1|1996-04-19|MACHINE AND METHOD FOR SORTING VARIOUS OBJECTS USING AT LEAST ONE ROBOTIZED ARM
    CN106345700B|2018-07-10|Quality Parameters in Orange conveys online and size fractionation equipment
    CA3020716A1|2017-11-02|Method and device for orienting an umbilicated fruit, in particular for packaging same
    EP1736250B1|2009-09-02|Process of merging letters and large or non-machine-treatable postal items into a single postman's walk
    JP2021503604A|2021-02-12|Automated aircraft aluminum scrap classification system based on laser-induced breakdown | technology
    EP2145175B1|2019-12-25|Method and machine for inspecting transparent or translucent articles
    EP3383597A1|2018-10-10|Method and facility for composing a batch of parts from parts situated in different storage areas
    JP2021522070A|2021-08-30|Recycling coins from scrap
    WO2011030042A1|2011-03-17|Method of aiding the identification of non-compliant products sorted manually and installation for the implementation thereof
    FR2868971A1|2005-10-21|Object or product identifying and sorting out method for supermarket, involves comparing individual identification code with objects individual identification code, and controlling guiding unit based on comparison result
    EP3105014A1|2016-12-21|Method and apparatus for depositing individual products on non-indexed, planar holders having recesses
    EP3496874B1|2020-09-09|Method of merging postal objects with already sorted postal articles on a table
    FR3100140A1|2021-03-05|Sorting device for agricultural products, and corresponding method
    OA20142A|2021-12-13|Device for sorting physical defects on objects.
    FR3113661A1|2022-03-04|Bulk Item Dispensing System
    FR3026722A1|2016-04-08|METHOD AND DEVICE FOR INDIVIDUALIZING LOTS OF ARTICLES ON A CONVEYOR.
    同族专利:
    公开号 | 公开日
    US9682406B2|2017-06-20|
    DK3056288T3|2018-04-23|
    US20160228921A1|2016-08-11|
    FR3032366B1|2017-02-03|
    EP3056288B1|2018-03-14|
    EP3056288A1|2016-08-17|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    WO1998019799A1|1996-11-04|1998-05-14|National Recovery Technologies, Inc.|Teleoperated robotic sorting system|
    WO2009068792A2|2007-11-07|2009-06-04|Veolia Proprete|Method and device for selectively sorting objects|
    IT1258006B|1992-01-13|1996-02-20|Gd Spa|SYSTEM AND METHOD FOR THE AUTOMATIC COLLECTION OF OBJECTS|
    FR2725640B1|1994-10-12|1997-01-10|Pellenc Sa|MACHINE AND METHOD FOR SORTING VARIOUS OBJECTS USING AT LEAST ONE ROBOTIC ARM|
    US5675710A|1995-06-07|1997-10-07|Lucent Technologies, Inc.|Method and apparatus for training a text classifier|
    FR2842671B1|2002-07-22|2005-03-04|Inst Nat Rech Inf Automat|COMPRESSION OF DIGITAL DATA ROBUST TO TRANSMISSION NOISE|
    US20070208455A1|2006-03-03|2007-09-06|Machinefabriek Bollegraaf Appingedam B.V.|System and a method for sorting items out of waste material|
    EP2125253A4|2007-01-05|2012-05-30|Thomas A Valerio|System and method for sorting dissimilar materials|
    DE102007038837A1|2007-08-16|2009-02-19|BIBA - Bremer Institut für Produktion und Logistik GmbH|Method and device for converting piece goods|
    FI20106090A0|2010-10-21|2010-10-21|Zenrobotics Oy|Procedure for filtering target image images in a robotic system|
    US9067744B2|2011-10-17|2015-06-30|Kabushiki Kaisha Yaskawa Denki|Robot system, robot, and sorted article manufacturing method|
    JP6000579B2|2012-03-09|2016-09-28|キヤノン株式会社|Information processing apparatus and information processing method|
    JP6364836B2|2014-03-14|2018-08-01|セイコーエプソン株式会社|Robot, robot system, and control device|
    US9266148B2|2014-06-27|2016-02-23|Key Technology, Inc.|Method and apparatus for sorting|NL2011066C2|2013-06-28|2015-01-05|Ig Specials B V|Apparatus and method for sorting plant material.|
    FR3031048B1|2014-12-24|2016-12-30|Solystic|POSTAL SORTING MACHINE WITH FEED INPUT COMPRISING A ROBOTIC ARM AND A FLAT CONVEYOR|
    FR3032365B1|2015-02-10|2017-02-03|Veolia Environnement-VE|SELECTIVE SORTING PROCEDURE|
    CA2998544A1|2015-09-11|2017-03-16|Berkshire Grey, Inc.|Robotic systems and methods for identifying and processing a variety of objects|
    US10730078B2|2015-12-04|2020-08-04|Berkshire Grey, Inc.|Systems and methods for dynamic sortation of objects|
    CN108604091A|2015-12-04|2018-09-28|伯克希尔格雷股份有限公司|System and method for dynamically handling object|
    US9937532B2|2015-12-18|2018-04-10|Berkshire Grey Inc.|Perception systems and methods for identifying and processing a variety of objects|
    CN110199231A|2016-11-08|2019-09-03|伯克希尔格雷股份有限公司|System and method for handling object|
    EP3544911A1|2016-11-28|2019-10-02|Berkshire Grey Inc.|Systems and method for providing singulation of objects for processing|
    CN108144863A|2016-12-02|2018-06-12|朱塞佩·普里泰利G.P.咨询简易两合公司|The optimization manufacturing method and system of lean production in the panel production line of furniture industry|
    CA3045522A1|2016-12-06|2018-06-14|Berkshire Grey, Inc.|Systems and methods for providing for the processing of objects in vehicles|
    US10583553B2|2017-03-20|2020-03-10|Berkshire Grey, Inc.|Systems and methods for processing objects including an auto-shuttle system|
    CA3057334A1|2017-03-24|2018-09-27|Berkshire Grey, Inc.|Systems and methods for processing objects, including automated processing|
    CN110740954B|2017-04-18|2021-10-22|伯克希尔格雷股份有限公司|System and method for processing objects including a space efficient distribution station and automated output processing|
    US11200390B2|2017-04-18|2021-12-14|Berkshire Grey, Inc.|Systems and methods for separating objects using drop conveyors with one or more object processing systems|
    US11055504B2|2017-04-18|2021-07-06|Berkshire Grey, Inc.|Systems and methods for separating objects using a vacuum roller with one or more object processing systems|
    US11080496B2|2017-04-18|2021-08-03|Berkshire Grey, Inc.|Systems and methods for separating objects using vacuum diverts with one or more object processing systems|
    US11205059B2|2017-04-18|2021-12-21|Berkshire Grey, Inc.|Systems and methods for separating objects using conveyor transfer with one or more object processing systems|
    CN110770149A|2017-04-24|2020-02-07|伯克希尔格雷股份有限公司|System and method for providing separation of objects for processing using object movement redistribution|
    JP2018203480A|2017-06-07|2018-12-27|株式会社東芝|Sorting apparatus and sorting system|
    CN107661865A|2017-06-19|2018-02-06|福建南方路面机械有限公司|Building waste sorts front-end detection system|
    CN107214108A|2017-06-19|2017-09-29|太仓弘杉环保科技有限公司|A kind of Efficient intelligent produces and processes the method for work of system|
    JP6734306B2|2018-01-25|2020-08-05|ファナック株式会社|Article transport system and robot system|
    CN110856846A|2018-08-24|2020-03-03|胜宏科技（惠州）股份有限公司|Automatic PCB sorting system and method|
    CN109926354B|2019-03-18|2020-12-25|佛山市利普达机械配件有限公司|Conveying belt for logistics sorting|
    CN110328148B|2019-07-10|2021-06-08|广东华中科技大学工业技术研究院|Screen detection screening device|
    CN110756464A|2019-10-24|2020-02-07|北京京日东大食品有限公司|Bean selecting process for raw material beans|
    CN111359908A|2020-02-21|2020-07-03|苏州先迅检测科技有限公司|Automatic detection equipment|
    CN111570326A|2020-04-07|2020-08-25|西安航空学院|Electromechanical automatic material sorting device|
    CN111842178A|2020-06-18|2020-10-30|苏州小优智能科技有限公司|Assembly line shoe blank 3D scanning and intelligent sorting equipment and method|
    CN111805309B|2020-07-02|2021-07-20|哈尔滨工业大学|Full-automatic grinding machine for ultrasonic vibration auxiliary grinding of outer circle of hard and brittle single crystal cylinder|
    CN112337807A|2020-11-15|2021-02-09|李童|Automatic sorting device based on electronic commerce|
    法律状态:
    2015-12-29| PLFP| Fee payment|Year of fee payment: 2 |
    2016-08-12| PLSC| Publication of the preliminary search report|Effective date: 20160812 |
    2016-12-27| PLFP| Fee payment|Year of fee payment: 3 |
    2017-12-22| PLFP| Fee payment|Year of fee payment: 4 |
    2020-02-26| PLFP| Fee payment|Year of fee payment: 6 |
    2021-02-25| PLFP| Fee payment|Year of fee payment: 7 |
    2022-02-25| PLFP| Fee payment|Year of fee payment: 8 |
    优先权:
    申请号 | 申请日 | 专利标题
    FR1551084A|FR3032366B1|2015-02-10|2015-02-10|SELECTIVE SORTING PROCESS|FR1551084A| FR3032366B1|2015-02-10|2015-02-10|SELECTIVE SORTING PROCESS|
    EP16305055.2A| EP3056288B1|2015-02-10|2016-01-21|Selective sorting method and device|
    DK16305055.2T| DK3056288T3|2015-02-10|2016-01-21|SELECTIVE SORTING METHOD AND DEVICE|
    US15/040,220| US9682406B2|2015-02-10|2016-02-10|Selective sorting method|
    [返回顶部]