Robotic network architecture comprising set of tags
By using robots with tags and predetermined holders in robots in robot network architectures, the problem of identifying and detecting elements in the prior art under low light conditions is solved, achieving higher recognition and interaction reliability and lower mechanical complexity.
Patent Information
- Application Number
- CN202380075095.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-11-23
- Filing Date
- 2023-11-03
- Publication Date
- 2025-06-24
AI Technical Summary
Existing robots have difficulty identifying and detecting components including objects of any shape under low light conditions, and the mechanical complexity and unreliable visual marker detection methods of the prior art are insufficient.
By setting up a robot network architecture, a robot utilizing a set of tags and at least one predetermined holder, the tag contains information for identifying, positioning and operating elements by interpreting this information to identify and interact with any type of elements, including under low light conditions.
It enables robots to recognize and detect components including objects of any shape under low light conditions, reducing mechanical complexity and improving the reliability of recognition and interaction.
Smart Images

Figure CN120202093A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of robotics, and more particularly to humanoid robots. More precisely, the invention relates to a robotic network architecture including a set of tags, at least one robot including at least one predetermined gripper, the tags being configured to connect to elements and the robots being configured to interact with any type of element, in particular any type of object, including at least one tag. Background Art
[0002] Robots are known that include a single spherical wheel on which the entire robot rests. These types of robots are commonly referred to as "ballbots". These robots are capable of moving stably in all directions on a flat surface by means of a single spherical wheel.
[0003] In particular, robots are known that have a single spherical wheel, each robot including a torso, two arms, and an upper member. The torso is connected to the spherical wheel and is fixed relative thereto, each arm being connected to the torso by pivot connection means or by ball-and-socket joint means to allow each arm to move relative to the torso, and the upper member being connected to the upper part of the torso and being fixed relative thereto. The upper member of the robot includes at least one sensor configured to allow the robot to position itself in its environment. Such a robot is configured to move in all directions and use its arms to perform tasks, such as gripping an object.
[0004] To grip an object, the robot includes a gripper. The gripper is configured to allow the robot to grip an object of any shape.
[0005] Object-specific gripping systems are known, i.e., there are robots equipped with grippers configured to grip a single type of object, for example, a robot equipped with suction cups configured to allow the robot to grip a glass plate.
[0006] However, such a gripper system makes the robot single-task and specific to a single type of object.
[0007] To overcome the above problems, there are robots including a gripper system configured to grip an object of any shape. In particular, such a gripping system consists of a robotic paw configured to replicate the movement of a human hand. Such a system has a large number of components and high mechanical complexity.
[0008] In addition, it is known to add visual markers to an object to be gripped to allow a robot to identify the object, for example by means of image recognition using image processing software and / or neural network algorithms. This type of visual marker is suitable for being detected and processed by the robot. However, if the visual marker is not visible, if the light is too dim, or if the robot is too far away from it, such detection and the associated processing are impossible. In addition, these known techniques are not always reliable because, for example, the algorithms and software used may fail to identify the object.
[0009] Accordingly, the present invention aims to solve the above problems by providing a robotic network architecture comprising: a set of tags; and at least one robot comprising at least one predefined gripper; the tags being configured to be connected to elements, and the robot being configured to interact with any type of element comprising at least one tag so as to allow the robot to identify any element equipped with a tag, particularly including, in low light conditions, detecting and identifying elements that are at least initially not within the field of view of the robot, etc. Summary of the Invention
[0010] More precisely, the invention aims to provide a robotic network architecture comprising a set of tags, at least one robot comprising at least one predefined gripper, the tags being configured to be respectively connected to elements belonging to the robotic network and containing information for identifying said elements and / or information for positioning said elements and / or characteristic information of said elements and / or information regarding the ability of the elements to be gripped and / or operated and / or moved by the robot via the predefined gripper, the elements being objects and / or persons and / or locations, the robot being configured to interact with any element comprising at least one tag, and the robot comprising means for interpreting the identification and / or position and / or characteristic information and / or the ability of the element to be gripped and / or operated and / or moved by the robot, and means for determining its behavior relative to the element, particularly with regard to gripping and / or operating and / or moving the element.
[0011] Advantageously, the robotic network architecture further comprises a set of general gripping device equipment configured to be gripped by the predefined gripper, the general gripping device equipment being configured to be respectively connected to a set of objects of the set of elements, the general gripping device equipment comprising at least one of said tags, and the general gripping device equipment being configured to be gripped and / or operated and / or moved by the predefined gripper.
[0012] According to one embodiment, at least some of the tags of the set of tags each comprise a housing, a transmission antenna, and a battery, the transmission antenna and the battery being housed within the housing, and the robot comprising a receiving antenna configured to communicate with the transmission antenna.
[0013] In particular, the general gripping device apparatus includes a body and at least one connecting device, the body being configured to be gripped by the predetermined gripper, and the connecting device being configured to connect the body to the object, the body extending mainly in a longitudinal direction between a first end and a second end, and the capsule being received in a cavity provided at one of the ends of the body.
[0014] Advantageously, at least some of the tags further include at least one button, the button being arranged on the outer surface of the capsule and being configured to activate / deactivate the tag and / or call the robot and / or send a predetermined message to the robot.
[0015] Advantageously, at least some of the tags further include at least one inertial measurement unit, the inertial measurement unit being configured to detect the movement or orientation of the element equipped with it.
[0016] Advantageously, at least some of the tags further include a Bluetooth chip coupled to the transmission antenna.
[0017] In one embodiment, the Bluetooth chip complies with standard 5.1 or higher and includes a direction-finding function for determining the angle of arrival relative to an object that is also equipped with a Bluetooth chip that complies with standard 5.1 or higher and includes a compatible direction-finding function. Description of the Drawings
[0018] The present invention will be better understood by reading the following description, which is given by way of example and with reference to the following drawings, which are given as non-limiting examples, in which the same reference numerals are given to similar objects, and in which:
[0019] Figure 1 shows an isometric view of a tag in the form of a tag with a capsule;
[0020] Figure 2 shows a side view of a tag with a capsule;
[0021] Figure 3 is a schematic front view of a tag including a capsule and an external electrical connector;
[0022] Figure 4 shows a general gripping device apparatus including a tag;
[0023] Figure 5 is a schematic diagram of a robot capable of interacting in a robot network architecture.
[0024] It should be noted that the accompanying drawings elaborate on the invention in detail for implementing the invention; although non - restrictive, the accompanying drawings can of course be used to further define the invention where appropriate. Detailed Description of the Invention
[0025] The invention relates to a robot network architecture, which includes a set of tags and at least one robot, and the robot includes at least one predefined gripper. The tags are configured to connect to an element and contain information for identifying the element, as well as information for allowing the element to be located and / or other information for allowing the robot to determine the action to be taken on the element. By virtue of the information contained in the tags, the robot can in particular determine whether it has the possibility, especially the ability and / or right, to grip and / or operate and / or move the said element, especially through the predefined gripper device. The robot is configured to interact with any type of element including at least one tag, and the robot includes means for interpreting the identification information and any other information contained in the tag.
[0026] The elements are especially objects, but they can also be people or locations.
[0027] Referring to Figure 1 and Figure 2 , the tag 30, also called "the tag", is first of all a device for identifying environmental elements in a robot network. For this purpose, the tag 30 includes information for identifying the element associated with it. This identification information is, for example, a unique identifier or a name. The tag 30 allows one or more robots in the robot network to detect the presence of the equipped element and name it. The tag 30 can also be used by the robot to determine the location of the equipped element. The tag can be a tag attached to the element, for example glued, and includes a specific color, code or pattern that the robot can decode through image analysis.
[0028] The tag 30 can also include a housing that contains means for communicating with the robot in order to trigger actions on its part, indicate action priorities, transmit data obtained from sensors carried by the element, etc. For these purposes, the tag can include a memory and a transmission antenna, such as a Bluetooth antenna.
[0029] In one embodiment, the tag 30 can in particular contain information related to the element associated with it, such as its descriptive name, in addition to the identifier, especially the unique identifier. In particular, such information can include the status of the person equipped with the tag, for example giving them an administrator status and authorizing them to give further instructions for the robot to execute. If the person equipped with the tag is not an administrator, certain instructions may not be executed by the robot depending on the information on the tag they wear.
[0030] The tag 30 may include information that allows the robot to locate the element carrying it or surrounding elements, either through direct position information or through the Bluetooth AoA function described below.
[0031] Optionally, the tag 30 may include information corresponding to the characteristics of the element it carries, such as its size, weight, or the behavior the robot is to adopt in terms of gripping and / or handling and / or moving, etc.
[0032] This information can be transmitted to the robot via a communication device, particularly a Bluetooth antenna housed in the housing forming part of the tag 30, so as to allow the robot to identify the element and facilitate interaction with it.
[0033] The tag 30 can also be connected to external peripheral devices 31, 32, particularly via I2C pins provided on the back of the tag, and thus transmit the information contained therein to the robot. For example, the tag 30 may include an external electrical connector 32 configured to allow the battery of the tag, or even the object equipped with the tag, to be recharged, or a four-pin external electrical connector 101 configured to allow peripheral devices external to the tag, such as sensors, communication devices, etc., to be connected to the tag.
[0034] According to an embodiment shown in Figures 1 to 4 the tag 30 includes a housing for accommodating any communication device and memory, and a button for transmitting a signal to the robot. For example, when the robot is nearby, i.e., within the radius allowing the robot to detect the tag, a person can activate this button present on the tag attached to the element of the robot network.
[0035] This button can be used, for example, to activate or deactivate the tag 30, to send a signal to call the robot, to give a specific characteristic to the element equipped with it, such as being an object of interest for the robot, or a temporary prohibited area, etc.
[0036] This button can also be used to call the robot or send it a predefined message.
[0037] As already mentioned, the tag can be associated with different categories of elements, such as areas for handling objects to be gripped, which can be recognized as, for example, placement areas, in a building, on a wall or a door, etc., thus allowing the robot to semantically identify these elements and determine the behavior it can adopt towards them.
[0038] The tag 30 can also be worn by a person, thus allowing the robot to identify them and interact with them.
[0039] In particular, the tag 30 can be used to define a region of interest in the environment in which the robotic network architecture is deployed, and by means of an information device included in the tag 30 and interpretable by the robot, generate specific instructions for the robot, such as: restricted areas, authorized areas, deceleration areas, etc.
[0040] In the robotic network architecture, the robot can thus be configured to include a database that allows the tag 30, i.e., the information contained in the tag, to be associated with the type of element with which it is associated. Depending on the type of element, the robot will be configured to take appropriate actions.
[0041] For example, a "processing" element can move, but a "zone" element or a "person" element cannot. However, the robot can potentially receive instructions from a "person" element, e.g., if they are authorized persons, depending on the instructions received, etc.
[0042] In particular, the tag 30 includes a battery, which can also be housed in the housing. The size of the battery is determined such that it can power the tag 30, preferably for at least several months.
[0043] According to the present invention, a robot can be "taught" to recognize and interpret new tags 30 associated with the elements of the robotic network architecture. For example, in order to define a new association between a tag 30 and an element, a user can expose the tag 30 near the robot and associate a semantic description with it, such as "this tag is a water bottle". The recognition of the tag 30 is stored in the robot's database and associated with the name "water bottle". If the tag 30 is associated with a process, the robot will know that it can move the "water bottle" because the tag 30 includes information interpretable by the robot, i.e., the element associated with the tag 30 is a "processing" element and this type of element is movable, and the process is in practice attached to or forms a component of the associated water bottle.
[0044] Thus, when operating the robotic network, once an element has been associated with a tag 30 (processing, placement area, etc.), instructions can be given to the robot with reference to the tag, such as:
[0045] 1. "Pick up the water bottle and place it on the table in the placement area";
[0046] 2. "Follow me";
[0047] 3. "Go to area A";
[0048] 4. etc.
[0049] In one embodiment, charging of the battery of the tag 30 is provided, in particular by means of a charging station capable of charging several tags simultaneously.
[0050] InFigures 1 to 4 In the embodiment shown, the tag 30 consists of a Bluetooth transmitter with AoA (angle-of-arrival) functionality, which allows a robot, equipped with a Bluetooth AoA receiving antenna itself, to determine the direction in which the tag 30 is located. In this way, the Bluetooth AoA chip in the tag 30 is configured to communicate with the robot and indicate to it the angular position of the tag 30 and, for example, its unique identifier.
[0051] In a robotic network architecture including a number of fixed or mobile elements equipped with such tags 30, the robot thus performs a number of measurements at different positions of the robot. The robot may thus include means for determining the position of each tag 30 by radio direction finding, by virtue of the AoA functionality and appropriate determination means, by triangulating the Bluetooth signals originating from each said tag 30.
[0052] The tag 30 may also include an inertial measurement unit housed in a housing for detecting the movement of the element equipped with it. Such an inertial measurement unit may also be configured to allow the correct orientation of the element associated with the tag 30, particularly when the element is gripped, manipulated or moved by the robot, or to assist in identifying the position of the corresponding element.
[0053] The tag 30 may also be associated with one or more sensors.
[0054] In particular, the tag 30 constitutes the only semantic recognition means of the element equipped with it from the perspective of the robot. In other words, the tag constitutes unique identification information, preferably associated with other information relating to the element equipped with it, particularly including structural and / or functional characteristics. By virtue of the tag 30, the elements equipped with it and external to the robot form part of the robotic network within which the robot can determine the actions it can take with respect to these elements.
[0055] Elements are classified into different types, including objects, people and locations. Subtypes may be defined to form classes of, for example, objects, locations or people. This makes it possible to simplify the categories of possible interactions between the robot and these elements, depending on whether the element belongs to an element type (location, person or object) and, for the element type, whether it belongs to a class.
[0056] For example, the robot will not consider a region, a person or an object belonging to the class of grippable objects to be equivalent. The tag 30 in a region makes it possible to identify positions to which the robot can or cannot move, or rooms into which the robot can or cannot enter. In another example, the tag 30 on an object may be used to indicate to the robot whether the object is grippable and movable.
[0057] Thus, more generally, tag 30 opens up a generation space for the robot because the presence of tag 30 in the robot network architecture creates an environment that allows for the automation of predefined tasks, such as moving between different objects at a given time, returning an object to a previously defined point when the object has been moved, and so on. This is possible because the objects are elements equipped with tag 30, the people giving the instructions are equipped with tags authorizing them to do so, and the positions where the objects move are elements equipped with tags.
[0058] As previously described, the robot network architecture according to the present invention includes at least one robot adapted to interact with elements equipped with tags.
[0059] In particular, the robot can be robot 10, which includes a single spherical wheel 2 configured to contact the ground, and a platform 3 mounted on the spherical wheel 2 by a stabilizing device, as shown in Figure 4 . Robot 10 is placed on spherical wheel 2 through platform 3. This type of robot 10 is commonly referred to as a "ballbot".
[0060] Robot 10 can move stably in all directions on the ground through a single spherical wheel 2.
[0061] Robot 10 includes a torso 5, at least one arm 4 and an upper member 7.
[0062] In particular, torso 5 is connected to platform 3 on one hand and to upper member 7 on the other hand, and at least one arm 4 is connected to torso 5 by a pivot joint or a ball-and-socket joint.
[0063] Robot 10 can include multiple arms 4, preferably two arms, like a humanoid robot. As shown in Figure 4 , robot 10 thus includes two arms 4, on either side of torso 5, each arm 4 having a forearm portion and an upper arm portion, joined by a joint. At the end of each arm 4, the robot includes a gripper 6, particularly similar to a claw. Gripper 6 is preferably predefined and can have any shape or function: claw, pincer, suction cup, etc.
[0064] Robot 10 preferably has an upper member 7 forming a head, which is equipped with an optical sensor, particularly a camera.
[0065] According to an embodiment of the robot network architecture, some elements are associated with a general gripper device dedicated to the robot gripper and include tags. In particular, each general gripper device is configured to connect to "any type" of object, and it includes tag 30, which contains information for identifying the object and potentially other information, as described above.
[0066] The gripper 6 of the robot 10 is thus suitable for interacting with the said elements of a suitable type, in particular "object" elements, by means of the universal gripping device equipment 1, which universal gripping device equipment 1 has a label 30 or a label attached thereto. In particular, the universal gripping device equipment 1 is specifically configured to be easily gripped by the predefined gripper 6 of the robot 10.
[0067] Example, such universal gripping device equipment as shown in Figure 5 . The universal gripping device equipment 1 is configured to be grippable by a predefined robot gripper 6. The universal gripping device equipment 1 is in particular configured to be connected to a set of objects and includes a label 30, which is received in a cavity at one end of the universal gripping device equipment 1.
[0068] The universal gripping device equipment 1 example includes a body and at least one connecting device, the body being configured to be grippable by a predefined gripper 6, and the connecting device being configured to connect the body to the object, the body extending mainly in a longitudinal direction between a first end and a second end, and the capsule being received in a cavity provided at one of the ends of the body.
[0069] According to one embodiment, the robot network architecture includes a database that is updated regularly. The database example contains the positions of the labels 30. It is updated when the robot 10 moves. In particular, the robot 10 is configured to detect the presence and direction of nearby active tags 30 by means of an embedded antenna and estimate their distance. The robot 10 can then be configured to update the database as it moves within the robot network, thus allowing it to move towards given tags 30 as per instructions. Once in proximity, the position will allow the robot 10 to manoeuvre and approach the said label 30 to an interaction distance.
[0070] The present invention is not limited to the embodiments described above, but extends to any equivalent embodiments.
Claims
1. A robot network architecture, comprising a set of tags, at least one robot (10) including at least one predefined gripper (6), the tags (30) being configured to be respectively connected to elements, the elements belonging to the robot network and containing information for identifying the elements and / or information for positioning the elements and / or characteristic information of the elements and / or information regarding the ability of the elements to be gripped and / or operated and / or moved by the robot (10) by means of the predefined gripper (6), the elements being objects and / or persons and / or positions, the robot (10) being configured to interact with any element including at least one tag (30) and the robot (10) including means for interpreting the identification and / or position and / or characteristic information and / or the ability of the elements to be gripped and / or operated and / or moved by the robot (10), and means for determining the behavior relative to the elements, particularly in terms of gripping and / or operating and / or moving the elements.
2. The robot network architecture according to claim 1, characterized in that Further comprising a set of general gripper device equipment (1), the general gripper device equipment (1) being configured to be gripped by the predefined gripper (6), the general gripper device equipment (1) being a set of objects configured to be respectively connected to a set of elements, the general gripper device equipment (1) including at least one of the tags (30), and the general gripper device equipment (1) being configured to be gripped and / or operated and / or moved by the predefined gripper (6).
3. The robot network architecture according to any one of claims 1 and 2, characterized in that, Each of at least some of the tags (30) of the set of tags includes a housing, a transmission antenna, and a battery, the transmission antenna and the battery being accommodated in the housing, and the robot (10) including a receiving antenna configured to communicate with the transmission antenna.
4. The robot network architecture according to claims 2 and 3, characterized in that, The general gripper device equipment (1) includes a body and at least one connecting device, the body being configured to be gripped by the predefined gripper (6) and the connecting device being configured to connect the body to the object, the body mainly extending between a first end and a second end in a longitudinal direction, and the housing being accommodated in a cavity provided at one of the ends of the body.
5. The robot network architecture according to claim 3 or 4, characterized in that At least some of the tags (30) further include at least one button, the button being arranged on an outer surface of the housing and configured to activate / deactivate the tag (30) and / or to call the robot (10) and / or to send a predefined message to the robot (10).
6. The robot network architecture according to any one of claims 3 to 5, characterized in that At least some of the tags (30) further include at least one inertial measurement unit, the inertial measurement unit being configured to detect the movement or direction of the element equipped therewith.
7. The robot network architecture according to any one of claims 3 to 6, characterized in that At least some of the tags (30) further include a Bluetooth chip connected to the transmission antenna.
8. The robot network architecture according to claim 7, wherein the Bluetooth chip complies with standard 5.1 or higher and includes a direction finding function for determining the angle of arrival relative to an object also equipped with a Bluetooth chip that complies with standard 5.1 or higher and includes a compatible direction finding function.