Robotic and motorized doors

Abstract

This application discloses a robot and an electric gate. The robot includes: a recognition sensor, a detection module, a first interaction module, and a first control module; the detection module is used to determine the position of a target electric gate using the recognition sensor; the first interaction module is used to send a first command to the target electric gate, the first command being used to control the target electric gate to open; the first control module is used to adjust the robot's posture based on the position of the target electric gate, thereby controlling the robot to pass through the target electric gate.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a robot and an electric door. Background Technology

[0002] In certain scenarios, mobile robots may need to pass through electric gates.

[0003] However, in related technologies, the use of electric doors by robots has problems such as high cost, low precision, and complex user operation. Utility Model Content

[0004] To address the related technical issues, embodiments of this application provide a robot and an electric door.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a robot, including: an identification sensor, a detection module, a first interaction module, and a first control module; wherein,

[0007] The detection module is used to determine the position of the target electric door using the identification sensor;

[0008] The first interaction module is used to send a first instruction to the target electric door, the first instruction being used to control the target electric door to open;

[0009] The first control module is used to adjust the robot's posture based on the position of the target electric gate, so as to control the robot to pass through the target electric gate.

[0010] In the above scheme, the detection module is further used for:

[0011] Using the identification sensor, identify points that are associated with the target electric gate;

[0012] The position of the target electric gate is determined based on the detected marker points if one or more of the following conditions are met:

[0013] One or more preset target markers were detected;

[0014] The number of detected markers is greater than or equal to the first threshold.

[0015] In the above scheme, the detection module is also used to use the recognition sensor to detect whether there are obstacles within a preset range that are related to the target electric door;

[0016] The first interaction module is further configured to send the first instruction to the target electric door when the detection module detects that there is no obstacle within the preset range.

[0017] In the above scheme, the first control module is further configured to execute a corresponding processing strategy based on the type of obstacle when the detection module detects an obstacle within the preset range.

[0018] In the above scheme, the first control module is further configured to control the robot to perform a target operation when the obstacle includes a target animal, the target operation being used to drive away the target animal.

[0019] In the above scheme, the detection module is further used to detect whether the robot has successfully passed through the target electric gate using positioning technology;

[0020] The first interaction module is further configured to send a second instruction to the target electric gate when the detection module detects that the robot has successfully passed through the target electric gate, the second instruction being used to control the target electric gate to close.

[0021] In the above scheme, the first interaction module is further used to obtain first information of the target electric door, the first information including relevant information of the working status of the target electric door;

[0022] The detection module is also used to perform fault detection on the target electric door based on the first information.

[0023] In the above scheme, the first interaction module is also used to actively or passively establish a communication connection with one or more electric doors, establish and store the association between the robot and the one or more electric doors, wherein the one or more electric doors include at least the target electric door.

[0024] This application embodiment also provides an electric gate, including: one or more feature identification components and a gate body component, wherein the feature identification component is disposed on the gate body component, and the feature identification component includes an identification point, the identification point including one or more of the following:

[0025] The features identify the corners and / or endpoints of the component shape;

[0026] Distinguishing it from the color difference points around the feature identification component;

[0027] The feature identifies the differences in material texture of the component;

[0028] The feature identification component is used for identification by the robot;

[0029] The electric door further includes: a second interaction module and a second control module; wherein...

[0030] The second interaction module is used to receive a first instruction sent by the target robot. The first instruction is used to control the electric door to open. The first instruction is sent by the target robot after determining the position of the electric door using its own recognition sensors.

[0031] The second control module is used to respond to the first command and control the electric door to open.

[0032] In the above scheme, the feature identification component includes more than three identification points, and the identification points are not collinear in the plane parallel to the door component.

[0033] In the above scheme, the feature identification component includes more than three identification points, the identification points are not collinear in the plane parallel to the door component, and at least three of the identification points are located at a height of not less than 30 centimeters (cm).

[0034] In the above scheme, the second interaction module is also used to receive a second instruction sent by the target robot. The second instruction is used to control the electric door to close. The second instruction is sent by the target robot when it detects that it has successfully passed through the electric door.

[0035] The second control module is also used to respond to the second command and control the electric door to close.

[0036] In the above scheme, the second interaction module is further used to send first information to the target robot so that the target robot can perform fault detection on the electric door. The first information includes relevant information about the working status of the electric door.

[0037] In the above scheme, the second interaction module is also used to actively or passively establish a communication connection with one or more robots, establish and store the association between the electric door and the one or more robots, wherein the one or more robots include at least the target robot.

[0038] The robot and electric gate provided in this application embodiment include: a recognition sensor, a detection module, a first interaction module, and a first control module; wherein, the detection module is used to determine the position of the target electric gate using the recognition sensor; the first interaction module is used to send a first command to the target electric gate, the first command being used to control the target electric gate to open; the first control module is used to adjust the robot's posture based on the position of the target electric gate, so as to control the robot to pass through the target electric gate. The solution provided in this application embodiment, by setting a recognition sensor on the robot, enables the robot to have the ability to recognize (i.e., detect) electric gates. When the robot needs to pass through a specific electric gate (i.e., the target electric gate), it can use the recognition sensor to determine the position of the electric gate, control the electric gate to open, and automatically pass through the electric gate based on the position. Thus, the accuracy of the robot's electric gate position detection can be effectively improved through the recognition sensor, and the robot can automatically pass through the electric gate without increasing the cost of the electric gate, eliminating the need for the user to manually open the electric gate. This significantly improves the robot's intelligence level and reduces the complexity of user operation, thereby enhancing the user experience. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the robot structure according to an embodiment of this application;

[0040] Figure 2 This is a schematic diagram illustrating a binding process between a robot and an electric door according to an embodiment of this application;

[0041] Figure 3 This is a schematic diagram illustrating another binding process between the robot and the electric door according to an embodiment of this application;

[0042] Figure 4 This is a schematic diagram illustrating the creation of a passageway through an electric gate in a robot map, as described in an embodiment of this application.

[0043] Figure 5 This is a schematic diagram of the robot vision inspection process for an electric door according to an embodiment of this application;

[0044] Figure 6 This is a schematic diagram illustrating the process of establishing a Bluetooth connection between the electric door and the robot according to an embodiment of this application.

[0045] Figure 7 This is a schematic diagram of the electric door structure according to an embodiment of this application;

[0046] Figure 8 This is a schematic diagram of the feature marking component structure located on the front and back sides in an embodiment of this application;

[0047] Figure 9 These are schematic diagrams of the feature marking components at different heights in embodiments of this application;

[0048] Figure 10 This is a schematic diagram of the door component structure with a double-door configuration according to an embodiment of this application;

[0049] Figure 11 A schematic diagram of a door component with air holes provided in an embodiment of this application;

[0050] Figure 12 This is a schematic diagram of a door component structure with nested sub-doors and a double-door structure, as described in an embodiment of this application.

[0051] Figure 13 This is a flowchart illustrating the electric door positioning method according to an embodiment of this application;

[0052] Figure 14 This is a schematic diagram of the electric door structure of a lawnmower according to an embodiment of this application;

[0053] Figure 15 This is a schematic diagram of the electric door positioning device according to an embodiment of this application;

[0054] Figure 16 This is a schematic diagram of the processing device structure according to an embodiment of this application. Detailed Implementation

[0055] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0056] First, let's take a lawnmower robot as an example to describe the problems associated with using electric gates for this technology. Lawnmower robots often need to mow multiple areas in a single task. However, in many scenarios, these lawns are often separated by obstacles such as walls or fences, preventing the robot from passing through. One approach is to install electric gates on these obstacles, allowing the robot to open them by collision. However, this method can easily damage the robot, and pets can easily escape through the gates. Alternatively, a camera can be installed on the electric gate to detect the robot and then open it. However, this method may increase the cost of the electric gate and may result in false detections leading to ineffective opening. Another approach is to require the user to open the gate for the robot via a gateway after detecting it. However, this method may increase the user's workload and significantly impact the user experience.

[0057] As can be seen from the above description, the related technologies using electric doors for robots have problems such as high cost, low precision, and complex user operation.

[0058] Based on this, in various embodiments of this application, by setting a recognition sensor on the robot, the robot is equipped with the ability to recognize (i.e. detect) electric doors. When the robot needs to pass through a specific electric door, the recognition sensor can be used to determine the position of the electric door, control the electric door to open, and automatically pass through the electric door based on the position. In this way, the accuracy of the robot's electric door position detection can be effectively improved by the recognition sensor. Moreover, the robot can automatically pass through the electric door without increasing the cost of the electric door, without the need for the user to manually open the electric door. This can significantly improve the robot's intelligence level and reduce the complexity of user operation, thereby improving the user experience.

[0059] It should be noted that in the various embodiments of this application, "one or more" means at least one or more items, and "multiple" means at least two or more items.

[0060] This application provides a robot, such as Figure 1 As shown, the robot includes: a recognition sensor 101, a detection module 102, a first interaction module 103, and a first control module 104; wherein,

[0061] The detection module 102 is used to determine the position of the target electric door using the identification sensor 101;

[0062] The first interaction module 103 is used to send a first instruction to the target electric door, the first instruction being used to control the target electric door to open;

[0063] The first control module 104 is used to adjust the robot's posture based on the position of the target electric gate, so as to control the robot to pass through the target electric gate.

[0064] In practical applications, the specific type of the identification sensor 101 can be set as needed, such as a radar identification sensor, a visual identification sensor (which may specifically include a camera, etc.), an infrared identification sensor, etc., and this application embodiment does not limit this. Furthermore, it can be understood that based on the setting of the identification sensor 101, the robot is a mobile robot with identification capabilities (such as radar identification capabilities, visual identification capabilities, infrared identification capabilities, etc.); the robot may specifically include a lawnmower robot (which can be simply called a lawnmower), an intelligent vehicle (which can be simply called a vehicle or car), etc., and this application embodiment does not limit the specific type and name of the robot.

[0065] In practical applications, the target electric gate can be understood as the electric gate that the robot needs to pass through, i.e., the electric gate to be passed through. The specific type of the target electric gate can be set as needed, and this application embodiment does not limit this. In addition, the specific method by which the robot determines the target electric gate can also be set as needed, and this application embodiment does not limit this either. For example, the first control module 104 can determine the target electric gate according to the task that the robot currently needs to perform, obtain a pre-set first path for passing through the target electric gate, and control the robot to move to the starting position of the first path; then, the first control module 104 can instruct (or control) the detection module 102 to determine the position of the target electric gate using the recognition sensor 101; wherein, the starting position of the first path can be understood as the approximate position of the target electric gate. Based on this position, the detection module 102 can use the recognition sensor 101 to perform position calibration on the target electric gate, i.e., determine the precise position of the target electric gate.

[0066] In practical applications, the detection module 102 can directly determine the position of the target electric gate or indirectly determine its position. Directly determining the position means that the detection module 102 can directly detect pre-set markers on the target electric gate using the identification sensor 101. These markers can include reflective strips / stickers, luminous stickers, stickers of specific colors, etc., serving an identification function and capable of being identified / detected. Indirectly determining the position means that the detection module 102 can first use the identification sensor 101 to detect markers pre-set on objects with a specific positional relationship to the target electric gate, determine the position of the object based on the detected markers, and then indirectly determine the position of the target electric gate based on the determined position of the object and the pre-set positional relationship between the object and the target electric gate. Here, objects with a specific positional relationship to the target electric gate can include fences, trees, houses, etc.

[0067] Based on this, in one embodiment, the detection module 102 can also be used for:

[0068] Using the identification sensor 101, identify points that are associated with the target electric gate are detected;

[0069] The position of the target electric gate is determined based on the detected marker points if one or more of the following conditions are met:

[0070] One or more preset target markers were detected;

[0071] The number of detected markers is greater than or equal to the first threshold.

[0072] In practical applications, the marker points can also be called feature marker points, feature points, key points, etc. This application embodiment does not limit the name of the marker points, as long as their function is achieved. Furthermore, the target marker points can be preset as needed, and the specific size of the first threshold can also be set as needed; this application embodiment does not limit this. Additionally, as can be seen from the above description, marker points associated with the target electric gate can include marker points preset on the target electric gate (such as reflective strips affixed to the target electric gate or its frame), and / or marker points preset on objects with a specific positional relationship to the target electric gate (such as reflective strips affixed to the edge of a fence surrounding the target electric gate). It should be noted that the specific type, specific setting method, and specific method of identifying the marker points can be found in the description of subsequent embodiments.

[0073] In practical applications, it can be understood that the first interaction module 103 can establish a communication connection between the robot and the target electric gate before sending the first instruction to the target electric gate. Furthermore, to improve the success rate of the robot passing through the target electric gate, before the first interaction module 103 sends the first instruction to the target electric gate, the detection module 102 can use a recognition sensor to detect whether there are obstacles around the target electric gate (hereinafter referred to as a preset range). If it is determined that there are no obstacles around the target electric gate, the first interaction module 103 then sends the first instruction to the target electric gate.

[0074] Based on this, in one embodiment, the detection module 102 can also be used to detect whether there are obstacles within a preset range that are associated with the target electric door using the identification sensor;

[0075] The first interaction module 103 can also be used to send the first instruction to the target electric door when the detection module 102 detects that there is no obstacle within the preset range.

[0076] In practical applications, the preset range can be set in advance as needed, such as a specific size area facing the target electric door, or a specific size area with an angle between it and the target electric door within a specific angle range. This application embodiment does not limit this.

[0077] In practical applications, considering that obstacles exist in different types, such as static obstacles and dynamic obstacles, different processing strategies can be set in advance on the first control module 104 for different types of obstacles. When the detection module 102 detects that there is an obstacle within the preset range, the first control module 104 can execute the corresponding processing strategy according to the type of obstacle.

[0078] Based on this, in one embodiment, the first control module 104 is further configured to execute a corresponding processing strategy based on the type of obstacle when the detection module 102 detects that there is an obstacle within the preset range.

[0079] In practical applications, the specific correlation between the type of obstacle and the processing strategy can be preset on the first control module 104 as needed. For example, assuming the identification sensor 101 is a visual recognition sensor, meaning the robot has visual recognition capabilities, when the detection module 102 determines the precise position of the target electric gate through visual recognition, it can simultaneously detect whether there are obstacles within the preset range, such as fixed obstacles or animals, and execute different processing strategies. Specifically, for fixed obstacles, the detection module 102 can notify the first control module 104 to use a preset specific strategy for intelligent obstacle avoidance; or, to ensure the robot can pass through the target electric gate, the first control module 104 can adjust the robot's posture to control the robot to push the obstacle aside (i.e., out of the preset range), and then the first control module 104 can continue to control the robot to pass through the target electric gate. For animals, the detection module 102 can determine whether the animal is a target animal (such as a user's pet) through visual recognition. If it is a target animal, the detection module 102 can notify the first control module 104 to perform a target operation to drive away the target animal. For example, the first control module 104 can play a specific audio clip at maximum volume to drive away the target animal, thereby preventing the user's pet from running outside when the electric door opens, reducing the risk of the pet getting lost, and improving the user experience.

[0080] Based on this, in one embodiment, the first control module 104 can also be used to control the robot to perform a target operation when the obstacle includes a target animal, the target operation being used to drive away the target animal.

[0081] In practical applications, the specific type of the target operation can be set as needed, such as playing a specific audio clip, adjusting the robot's posture to control the robot to follow the target animal, etc. This application embodiment does not limit this. Additionally, exemplarily, assuming the identification sensor 101 is a visual identification sensor, meaning the robot has visual recognition capabilities, the detection module 102 can be pre-set with a first visual model. This first visual model can be used to detect obstacles within a preset range, which may include the first path. After the robot establishes a communication connection with the target electric door, the detection module 102 can activate (i.e., turn on or call) the first visual model to check if there are any animals within the preset range and identify the animal's category. If the detection module 102 identifies the animal as the target animal (such as the user's pet, specifically including cats, dogs, etc.), the first interaction module 103 can temporarily refrain from sending the first instruction to the target electric door. The detection module 102 can then notify the first control module 104 to play a specific audio clip to drive away the target animal. The detection module 102 can re-detect for obstacles after waiting for a specified duration (the specific duration can be set according to requirements). If no obstacle is detected, the first interaction module 103 can send the first instruction to the target electric door.

[0082] In practical applications, in order to further reduce safety risks such as pets getting lost, the detection module 102 can detect whether the robot has successfully passed through the target electric gate. The first interaction module 103 can send a command to the target electric gate to control the target electric gate to close when the robot has successfully passed through the target electric gate.

[0083] Based on this, in one embodiment, the detection module 102 can also be used to detect whether the robot has successfully passed through the target electric gate using positioning technology;

[0084] The first interaction module 103 can also be used to send a second instruction to the target electric gate when the detection module 102 detects that the robot has successfully passed through the target electric gate. The second instruction is used to control the target electric gate to close.

[0085] In practical applications, the specific type of positioning technology used by the detection module 102 can be set as needed, such as real-time dynamic RTK (Real Time Kinematic) positioning technology, etc. This application embodiment does not limit this.

[0086] In practical applications, the criteria for determining whether the robot has successfully passed through the target electric gate can be set as needed, and this embodiment does not limit this. For example, assuming the identification sensor 101 is a visual identification sensor, meaning the robot has visual recognition capabilities, the detection module 102 can combine RTK positioning capabilities and visual recognition capabilities to detect whether the robot has successfully passed through the target electric gate. Furthermore, the detection module 102 can determine that the robot has successfully passed through the target electric gate if the robot's body does not collide with the gate itself, and / or if the robot passes through the target electric gate and the distance between the robot and the target electric gate is greater than or equal to a specific threshold (the specific value of this threshold can also be set as needed).

[0087] In practical applications, when the detection module 102 determines that the robot has successfully passed through the target electric gate, the first control module 104 can also control the robot to pause in place. Simultaneously, the first interaction module 103 can send the second instruction to the target electric gate. Furthermore, after determining that the target electric gate has returned a successful closing instruction (which can be referred to as the third instruction in the following description), the first interaction module 103 can actively disconnect its communication connection with the target electric gate. Subsequently, the first control module 104 can control the robot to continue working, such as passing through other electric gates besides the target electric gate, or moving to areas other than its current location. Here, if the first interaction module 103 does not receive the third instruction within a specific time period (the specific value of which can be set according to requirements), the first interaction module 103 can determine that the target electric gate has failed to close and can report an event to a specific device (such as a user terminal). This event can be used to notify the user that the target electric gate is abnormal, allowing the user to promptly troubleshoot the target electric gate.

[0088] In practical applications, after establishing a communication connection between the robot and the target electric door, the first interaction module 103 can obtain information reflecting the working status of the target electric door, such as its power level and logs (which can be referred to as the first information in the following description), based on the communication connection. The detection module 102 can check the working status of the target electric door based on this information, such as checking whether the target electric door has malfunctioned.

[0089] Based on this, in one embodiment, the first interaction module 103 can also be used to obtain first information of the target electric door, the first information including relevant information of the working status of the target electric door;

[0090] The detection module 102 can also be used to perform fault detection on the target electric door based on the first information.

[0091] In practical applications, the relevant information regarding the working status of the target electric door (i.e., the first information) may specifically include power consumption, logs, etc. This application embodiment does not limit the specific content of the first information. Furthermore, the specific method by which the detection module 102 performs fault detection on the target electric door based on the first information can also be set according to requirements, and this application embodiment does not limit this either. When the detection module 102 determines that the target electric door has an abnormality / fault, the first interaction module 103 can report an event to a specific device (such as a user terminal). This event can be used to notify the user that the target electric door has an abnormality / fault, thereby allowing the user to repair and adjust the target electric door in a timely manner; alternatively, the first interaction module 103 can instruct the target electric door to automatically repair and adjust.

[0092] In practical applications, the first interaction module 103 can pre-establish a binding relationship (or association relationship) between the robot and the target electric door, and subsequently communicate with the target electric door based on this binding relationship. Establishing the binding relationship between the robot and the target electric door means that after the first interaction module 103 initially establishes a communication connection with the target electric door, it records (i.e., stores) the unique identifier and communication address of the target electric door.

[0093] In practical applications, the specific communication method between the robot and the target electric gate can be set as needed, such as Bluetooth, mobile hotspot (Wi-Fi), etc., and this application embodiment does not limit this.

[0094] For example, when the robot and the target electric door communicate via Bluetooth, the communication address may specifically include a Bluetooth address. That is, the first interaction module 103 may specifically use Bluetooth to pair the electric door with the robot, or in other words, the first interaction module 103 may use Bluetooth to establish a binding relationship between the robot and the target electric door. Furthermore, considering that Bluetooth operating modes may include master mode and slave mode, the binding relationship between the robot and the target electric door can be established by the robot in master mode, meaning the first interaction module 103 can actively initiate a Bluetooth connection to the target electric door (i.e., initiate a Bluetooth connection request); or, the binding relationship between the robot and the target electric door can be established by the robot in slave mode, meaning the target electric door can initiate a Bluetooth connection to the first interaction module 103.

[0095] Here, as Figure 2As shown, the target electric gate can be denoted as MowGate. Assuming the robot is a lawnmower, and the lawnmower supports Bluetooth connection in slave mode (meaning it can only be connected to other devices, not actively connect to other devices like the MowGate via Bluetooth), and assuming the MowGate supports a master-slave hybrid Bluetooth connection mode (meaning it can switch between master and slave modes), meaning the MowGate can both be connected to other devices and actively connect to other devices (like the lawnmower), then establishing the binding relationship between the lawnmower and the MowGate can be achieved by the user through a specific application (referred to as an APP) installed on the terminal, providing operation guidance and information transfer. The operation guidance and information transfer via the APP means that: the APP can first establish a Bluetooth connection with the lawnmower, obtain the lawnmower's Bluetooth address information through Bluetooth and cache it locally in the APP; then, the APP can establish a Bluetooth connection with MowGate, and transmit the lawnmower's Bluetooth address information to MowGate through Bluetooth; finally, MowGate can connect to the lawnmower through Bluetooth, that is, MowGate can search for the lawnmower based on the lawnmower's Bluetooth address information provided by the APP and establish a Bluetooth connection with the lawnmower.

[0096] Specifically, such as Figure 3 As shown, the process of binding the lawnmower to MowGate may include the following steps:

[0097] Step 301: The APP establishes a Bluetooth connection with the lawnmower, obtains and stores the lawnmower's Bluetooth address information;

[0098] Step 302: The APP searches for MowGate in the mode and establishes a Bluetooth connection, transmitting the lawnmower's Bluetooth address information to MowGate;

[0099] Step 303: MowGate establishes a Bluetooth connection with the lawnmower and transmits its own Bluetooth address to the lawnmower;

[0100] Step 304: The APP searches for lawnmowers that have disconnected from MowGate, establishes a Bluetooth connection, and obtains the binding result.

[0101] In step 301, the user can operate the APP to establish a Bluetooth connection between the lawnmower and the APP. After that, the APP can send a Bluetooth connection command to the lawnmower, and the lawnmower and the APP establish a Bluetooth connection. After that, the lawnmower can return the result and Bluetooth address information to the APP, and the APP can record the Bluetooth address information of the lawnmower.

[0102] In step 302, the user can operate the app to establish a Bluetooth connection between the app and MowGate. Afterward, the app can inform the lawnmower that the user does not need to press the OK button on the lawnmower before the next Bluetooth connection (only the app and MowGate can connect to the lawnmower via Bluetooth). This step avoids the user manually operating the lawnmower (i.e., pressing the OK button on the lawnmower) to allow the Bluetooth connection each time; this operation only needs to be performed once when establishing the binding relationship between the lawnmower and MowGate. Afterward, the app can actively disconnect from the lawnmower via Bluetooth, search for MowGate in slave mode, and return the search results. Afterward, the user can operate the app... Select the MowGate to be bound. The app establishes a Bluetooth connection with the MowGate and transmits the lawnmower's Bluetooth address information. The app can then set a timer to connect to the lawnmower after 10 seconds and obtain the connection result (it can continue to try for 20 seconds). Afterward, the MowGate can establish a Bluetooth connection with the app and store the lawnmower's Bluetooth address information (if this Bluetooth address information has already been stored, it does not need to be saved again). The MowGate returns the connection result to the app. The app can then notify the MowGate to switch to primary mode and disconnect the Bluetooth connection with the MowGate. The MowGate can then switch to primary mode.

[0103] For step 303, a Bluetooth connection can first be established between the lawnmower and MowGate, and the MowGate's Bluetooth address information can be transmitted to the lawnmower. Then, if the lawnmower successfully stores the MowGate's Bluetooth address information, the lawnmower will announce a success message (referred to as "Successed"). If the lawnmower fails to store the MowGate's Bluetooth address, the lawnmower will announce a failure message (referred to as "Failed"). Afterward, the lawnmower can return the binding result to the MowGate. If the binding result is successful, the MowGate will remain in master mode, disconnect from the lawnmower's Bluetooth connection, and will not actively reconnect to the lawnmower's Bluetooth for 5 minutes. If the binding result is unsuccessful, the MowGate will switch to slave mode.

[0104] In step 304, the lawnmower can establish a Bluetooth connection with the APP and transmit the binding results; the APP can display the binding results.

[0105] In practical applications, the robot may also include a local storage module. After the first interaction module 103 establishes the binding relationship between the robot and the target electric gate, it can set the first path on the robot, that is, establish the binding relationship between the target electric gate and the first path on the robot, which means that the robot's local storage module stores the identifier of the target electric gate and related information such as the first path in a correlated manner. The first path is used to pass through the target electric gate, which can also be understood as the first path enabling the robot to pass through (i.e., through) the passage of the target electric gate. Furthermore, the storage format of the first path on the local storage module can be set according to requirements, and this embodiment does not limit this; for example, the first interaction module 103 can add the first path to the map stored in the local storage module and mark the existence of the target electric gate on the first path.

[0106] For example, such as Figure 4 As shown, the target electric gate can be denoted as MowGate. Assuming the robot is a lawnmower and the recognition sensor 101 is a visual recognition sensor (meaning the robot has visual recognition capabilities), although the lawnmower and MowGate are bound together to ensure communication, the lawnmower doesn't know the location of the MowGate and therefore cannot pass through it. Therefore, after the lawnmower and MowGate are bound together, the user can remotely control the lawnmower to establish a passage through the MowGate (i.e., the first path). The lawnmower can automatically record its position and coordinates during this process, thus establishing a passage through the MowGate in the map stored in the local storage module. Furthermore, the lawnmower can bind the established passage to the MowGate, marking the passage as a passage with an installed MowGate on the map stored in the local storage module. In this way, during subsequent work, the lawnmower can first automatically navigate to the passage through the MowGate (i.e., move to the starting position of the first path), then find the MowGate through visual recognition (i.e., use the recognition sensor 101 to determine the position of the target electric gate), perform position calibration, and then pass through the MowGate.

[0107] In practical applications, from the robot's perspective, a robot can establish a binding relationship with one or more electric gates, creating a "one vehicle, multiple gates" scenario. In this scenario, for each electric gate, the robot can store associated information such as the gate's identifier and the path used to pass through it. This information can be stored in the local storage module. From the electric gate's perspective, a single electric gate can establish a binding relationship with one or more robots, creating a "one gate, multiple vehicles" scenario. In this scenario, each robot can store associated information such as the electric gate's identifier and the path used to pass through it. This information can also be stored in the local storage module.

[0108] Based on this, in one embodiment, the first interaction module 103 can also be used to actively or passively establish a communication connection with one or more electric doors, establish and store the association relationship (also known as the binding relationship) between the robot and the one or more electric doors, and the one or more electric doors may include at least the target electric door.

[0109] In practical applications, as can be seen from the above description, the first control module 104 can obtain the first path from the local storage module, for example, from the map information stored in the local storage module. Then, the first control module 104 can navigate the robot to the first path, i.e., control the robot to move to the starting position of the first path. Here, the starting position of the first path can be considered as the approximate position of the target electric door. Based on this position, the detection module 102 can subsequently use the recognition sensor 101 to calibrate the position of the target electric door, i.e., determine the precise position of the target electric door. Furthermore, if the detection module 102 cannot determine the precise position of the target electric door using the recognition sensor 101, the first control module 104 can abandon controlling the robot to pass through the target electric door. Additionally, the first interaction module 103 can report an event to a specific device (such as a user terminal). This event can be used to notify the user that the target electric door is abnormal, allowing the user to promptly troubleshoot the target electric door.

[0110] In practical applications, when the identification sensor 101 is a visual recognition sensor (i.e., the robot has visual recognition capabilities), the detection module 102 can also be pre-set with a second visual model. This second visual model can be used to search for (i.e., determine) the precise location of the target electric door. After the first control module 104 controls the robot to move to the starting position of the first path, the detection module 102 can activate (i.e., turn on or call) the second visual model to determine the precise location of the target electric door. For example, the process by which the detection module 102 visually detects the target electric door by calling the second visual model can be as follows: Figure 5 As shown, assuming the robot and the target electric gate communicate via Bluetooth, and the target electric gate is denoted as MowGate, and the robot is assumed to be a lawnmower, firstly, the lawnmower's detection module 102 can detect MowGate, that is, detect whether the visual recognition sensor (such as a camera) can see (i.e., capture) MowGate, specifically determining whether the outline of MowGate is detected; then, if MowGate is detected, the detection module 102 can perform marker point matching; if a sufficient number of marker points are matched (i.e., if the number of detected marker points is greater than or equal to the first threshold), the detection module 102 can determine that the visual calibration is complete (at this time, the lawnmower can determine the precise location of MowGate), and can check the Bluetooth connection process to prepare for subsequent passage through MowGate. If the detection module 102 fails to detect the MowGate, or if the detection module 102 fails to match a sufficient number of marker points (i.e., the number of detected marker points is less than the first threshold), the first control module 104 of the lawnmower can abandon the current task of passing through the MowGate. The first interaction module 103 will then report an event to notify the user that the MowGate is abnormal. Afterward, the first control module 104 can end the current task. Furthermore, after ending the current task, the first control module 104 can determine whether passing through the MowGate is necessary to return to the charging station. If so, it can control the lawnmower to standby in front of the MowGate; otherwise, it can end the current mowing task and control the lawnmower to perform a return-to-charge task, i.e., control the lawnmower to navigate to the charging station for charging. Here, during the process of the detection module 102 using visual recognition to determine the location of the MowGate, the lawnmower can also be manually remotely calibrated against the marker points on the MowGate, thereby enabling the detection module 102 to determine the precise location of the MowGate.

[0111] In practical applications, as can be seen from the above description, the embodiments of this application include "one vehicle, multiple doors" and "one door, multiple vehicles" scenarios. That is, a robot can establish a binding relationship with one or more electric doors, and an electric door can establish a binding relationship with one or more robots. In the "one door, multiple vehicles" scenario, where the target electric door has established binding relationships with multiple robots, the target electric door can continuously query whether there are currently any connectable robots (i.e., bound robots within communication range) according to specific rules. After detecting a connectable robot, the target electric door can request to establish a communication connection with that robot. If the connection is successfully established, the target electric door can wait for the robot to actively disconnect before continuing to poll other unconnected, bound robots. If another connectable robot is detected, the target electric door can re-establish a communication connection with that robot, thereby realizing the "one door, multiple vehicles" scenario. Specifically, the target electric door can send communication connection requests to the multiple robots in turn according to the binding order between itself and the multiple robots.

[0112] For example, when Bluetooth communication is used between the robot and the target electric gate, the process of the target electric gate sending Bluetooth connection requests to the multiple robots in turn to establish a Bluetooth connection can be as follows: Figure 6 As shown, the target electric gate is denoted as MowGate, and it is assumed that the multiple robots are all lawnmowers. MowGate establishes a binding relationship with these three lawnmowers in the binding order of lawnmower 1, lawnmower 2, and lawnmower 3. When lawnmower 1 is not within the Bluetooth connection range of MowGate, but lawnmower 2 and lawnmower 3 are within the Bluetooth connection range of MowGate, the steps for MowGate to establish a Bluetooth connection with the lawnmowers may include:

[0113] Step 601: MowGate attempts to connect to lawnmower 1. If the connection fails after 5 seconds, it attempts to connect to lawnmower 2.

[0114] Step 602: MowGate and lawnmower 2 successfully established a Bluetooth connection;

[0115] Step 603: Lawn Mower 2 checks if it needs to connect to MowGate via Bluetooth, i.e., whether it needs to go through MowGate. If so, maintain the Bluetooth connection until Lawn Mower 2 goes through MowGate. Lawn Mower 2 can then perform the following steps: Figure 1 The robot demonstrates the door passage process and notifies MowGate to disconnect the Bluetooth connection after passing through MowGate.

[0116] Step 604: Lawnmower 2 notifies MowGate to disconnect Bluetooth;

[0117] Step 605: MowGate actively disconnects from the Bluetooth connection with lawnmower 2 and attempts to connect to lawnmower 3;

[0118] Step 606: MowGate and Lawn Mower 3 successfully established a Bluetooth connection;

[0119] Step 607: The lawnmower 3 checks whether it needs to connect to MowGate via Bluetooth, i.e., whether it needs to go through MowGate; if not, it notifies MowGate to disconnect the Bluetooth connection.

[0120] Step 608: The lawnmower 3 notifies MowGate to disconnect the Bluetooth connection;

[0121] Step 609: MowGate actively disconnects from the lawnmower 3 via Bluetooth, remains silent for a specified time (the specific duration can be set according to needs), and then reconnects to the lawnmower via Bluetooth in the same binding order.

[0122] Based on this, in one embodiment, when the target electric gate has established a binding relationship (i.e., an association relationship) with multiple robots, the first interaction module 103 can also be used to:

[0123] The robot receives a first request from the target electric gate. The first request is used to request the establishment of a communication connection between the robot and the target electric gate. The first request is sent by the target electric gate to the multiple robots in turn according to the binding order between the robot and the multiple robots.

[0124] Based on the first request, a communication connection is established between the robot and the target electric gate.

[0125] In practical applications, in a "one vehicle, multiple doors" scenario, where the robot has established a binding relationship with multiple electric doors, when the robot is within the communication range of the multiple electric doors, each of the multiple electric doors can send a communication connection request to the robot (hereinafter referred to as the second request). After receiving the second request, the robot can detect whether the second request is a communication connection request sent by the target electric door. If it is, the robot establishes a communication connection with the target electric door; otherwise, the robot can reject the second request.

[0126] Based on this, in one embodiment, when the robot has established a binding relationship (i.e., an association relationship) with multiple electric doors, the first interaction module 103 can also be used to:

[0127] The robot receives a second request from the first electric gate, the second request being used to request the establishment of a communication connection between the robot and the first electric gate, and the second request may at least include the identifier of the first electric gate;

[0128] If it is determined that the first electric door is the target electric door (for example, if the identifier of the first electric door is the same as the identifier of the target electric door), a communication connection is established between the robot and the target electric door based on the second request.

[0129] Here, if it is determined that the first electric door is not the target electric door, for example, if the identifier of the first electric door is different from the identifier of the target electric door, the first interaction module 103 may refuse to establish a communication connection between the robot and the first electric door.

[0130] Accordingly, embodiments of this application also provide an electric door, such as... Figure 7 As shown, the electric gate includes one or more feature identification components 701 and a gate body component 702. The feature identification component 701 is disposed on the gate body component 702 and includes identification points, which include one or more of the following:

[0131] The corners and / or endpoints of the shape of the feature identifier 701;

[0132] Distinguishing features from the color differences surrounding the 701 characteristic identification component;

[0133] The material texture differences of feature-identifying component 701;

[0134] The feature identification component 701 is used to be identified by the robot, that is, the identification point is used to be identified by the robot.

[0135] In one embodiment, such as Figure 7 As shown, the electric gate may further include: a second interaction module 703 and a second control module 704; wherein,

[0136] The second interaction module 703 is used to receive a first instruction sent by the target robot. The first instruction is used to control the electric door to open. The first instruction is sent by the target robot after determining the position of the electric door using its own recognition sensor.

[0137] The second control module 704 is used to respond to the first command and control the electric door to open.

[0138] In one embodiment, the second interaction module 703 can also be used to receive a second instruction sent by the target robot, the second instruction being used to control the electric door to close, the second instruction being sent by the target robot when it detects that it has successfully passed through the electric door;

[0139] Accordingly, the second control module 704 can also be used to respond to the second command and control the electric door to close.

[0140] In one embodiment, the second interaction module 703 can also be used to send first information to the target robot so that the target robot can perform fault detection on the electric door. The first information includes relevant information about the working status of the electric door.

[0141] In one embodiment, the second interaction module 703 can also be used to actively or passively establish a communication connection with one or more robots, establish and store the association between the electric door and the one or more robots, wherein the one or more robots include at least the target robot.

[0142] Here, the specific processing procedures of the electric door and its modules can be understood by referring to the above robot embodiment, and will not be repeated here.

[0143] In practical applications, each feature identifier 701 can be any non-closed graphic shape or structure capable of identification, and this application embodiment does not limit this. For example, the feature identifier 701 can be an "L", "N", "M", or other non-closed graphic. It should be noted that... Figure 7 The illustrated feature identifier 701 is exemplified by an "L" shape, but it is not limited to this; the feature identifier 701 can also be other shapes. Each feature identifier 701 can include one or more identifier points, including corner points, endpoints, color difference points, and material / texture difference points. Deep learning algorithms can accurately extract these identifier points in complex environments, providing basic data for subsequent pose calculations. Corner points, also known as extreme points, refer to points in the feature identifier 701 with local maximum curvature or significant gradient changes. Endpoints refer to the edge points of the feature identifier 701. Color difference points are points with significant color differences from the surrounding area of ​​the feature identifier 701. Material / texture points are points with significant material and texture differences from the surrounding area of ​​the feature identifier 701.

[0144] In practical applications, each feature identifier 701, when it is a non-closed shape, must have one or more corner points and / or endpoints. For example, when the feature identifier 701 is "L" shaped, it includes 3 identifier points, which include 1 corner point and 2 endpoints of the "L" shaped feature identifier 701; when the feature identifier 701 is "N" shaped, it includes 4 identifier points, which include 2 corner points and 2 endpoints of the "N" shaped feature identifier 701; when the feature identifier 701 is "M" shaped, it includes 5 identifier points, which include 3 corner points and 2 endpoints of the "M" shaped feature identifier 701.

[0145] In one embodiment, the electric gate may include a plurality of feature identification components 701, which are spaced apart on the gate body component 702.

[0146] In practical applications, each feature identification component 701 can be arranged on the door component 702 at the same interval or at different intervals. The interval can be any suitable range, and this embodiment does not limit this. This avoids feature confusion caused by overly concentrated arrangement of the feature identification components 701, while also ensuring that the robot's recognition sensors can capture multiple identifiable key points at different distances and angles, improving detection accuracy. For example, if the interval range is set to [10cm, 15cm], each feature identification component 701 can be arranged on the door component 702 at the same interval (e.g., 12cm horizontally and vertically) within this range, or at different intervals (e.g., 10cm horizontally and 15cm vertically).

[0147] In one embodiment, the feature identification component 701 may include a plurality of reflective or light-emitting elements.

[0148] In practical applications, each feature identification component 701 may include a reflective element or a light-emitting element, the shape of which is the same as that of the feature identification component 701. The reflective element can be made of any material, such as acrylic, plastic, rubber, or other materials. The light-emitting element can be made of any material, such as acrylic, LED flexible light strips, or metal. Furthermore, the reflective element can be made of a frosted material, which ensures good reflectivity while effectively reducing interference from reflections, thus improving the stability of the detection.

[0149] In one embodiment, the feature identification component 701 may include more than three identification points, and the identification points are not collinear in the plane parallel to the door component 702.

[0150] In practical applications, when the electric gate includes a single feature identifier 701, the feature identifier 701 includes more than three identifier points, and each identifier point is not collinear in a plane parallel to the gate body component 702; or, when the electric gate includes multiple feature identifier components 701, the sum of the identifier points included in the multiple feature identifier components 701 is greater than three, and each identifier point is not collinear in a plane parallel to the gate body component 702. That is, each identifier point is neither located in a plane parallel to the gate body component 702 nor arranged on the same straight line. This ensures that when the robot observes multiple feature identifier components 701 from any angle, the visual features formed by the multiple feature identifier components 701 are unique, avoiding feature misjudgment or information loss due to collinearity, thereby improving the accuracy and reliability of detection. For example, assuming that the plane containing the door component 702 is vertical, then the plane parallel to the door component 702 is also vertical. If there are three marker points that are neither located in any plane parallel to the door component 702 nor on the same straight line, then it can be determined that these three marker points are not collinear in the plane parallel to the door component 702.

[0151] In one embodiment, the feature identification component 701 may include more than three identification points, and at least three of the identification points are located at a height greater than 10cm.

[0152] In practical applications, when the electric gate includes a single feature identifier 701, the feature identifier 701 includes more than three identifier points, and at least three of these identifier points are located at a height greater than 10cm; or, when the electric gate includes multiple feature identifier components 701, the sum of the number of identifier points included in the multiple feature identifier components 701 is greater than three, and at least three of these identifier points are located at a height greater than 10cm. This solves the problem of occlusion by objects lower than 10cm, ensuring detection accuracy. For example, the height of a typical lawn may reach 10cm. To ensure that the feature identifier 701 is not obscured by the lawn and can be detected by the robot's recognition sensor, at least three of the identifier points must be located at a height greater than 10cm.

[0153] In one embodiment, the feature identification component 701 may include more than three identification points, the identification points are not collinear in a plane parallel to the door component 702, and at least three of the identification points are located at a height greater than 10cm.

[0154] In practical applications, when an electric gate includes a single feature identification component 701, this component has more than three identification points. Each identification point is not collinear in a plane parallel to the gate body component 702, and at least three of these points are at a height greater than 10cm. Alternatively, when an electric gate includes multiple feature identification components 701, the sum of the identification points in each component is greater than three. Each identification point is not collinear in a plane parallel to the gate body component 702, and at least three of these points are at a height greater than 10cm. For example, the height of a typical household lawn is maintained between 2cm and 6cm. When the grass grows to 3cm to 8cm, a lawnmower is used. To ensure that the lawnmower (robot) can accurately identify the markings on the gate even after the grass has grown tall, at least three identification points on the gate need to be at a height greater than 10cm.

[0155] In one embodiment, the feature identification component 701 may include more than three identification points, the identification points are not collinear in a plane parallel to the door component 702, and at least three of the identification points are located at a height of not less than 30cm.

[0156] In practical applications, when the electric gate includes a single feature identification component 701, this component includes more than three identification points. Each identification point is not collinear in a plane parallel to the gate body component 702, and at least three of these identification points are at a height of at least 30cm. Alternatively, when the electric gate includes multiple feature identification components 701, the sum of the identification points in each component is greater than three. Each identification point is not collinear in a plane parallel to the gate body component 702, and at least three of these identification points are at a height of at least 30cm. This solves the problem of occlusion by objects below 30cm, ensuring detection accuracy. For example, some shrubs or flowering plants can reach a height of 30cm. To ensure the robot is not obstructed and can accurately identify the markings on the gate, at least three identification points on the gate must be at a height of at least 30cm.

[0157] In one embodiment, such as Figure 8 As shown, the electric gate may include multiple feature marking components 701. The multiple feature marking components 701 include a first part feature marking component 701A and a second part feature marking component 701B. The first part feature marking component 701A is arranged at intervals on the first side of the gate body component 702. The second part feature marking component 701B of the multiple feature marking components 701 is arranged at intervals on the second side of the gate body component 702, and the first side and the second side are opposite to each other.

[0158] In practical applications, feature marking components 701 are provided on both the front and back of the door component 702. Specifically, multiple feature marking components 701 are divided into a first part (feature marking component 701A) and a second part (feature marking component 701B) according to their arrangement on the door component 702. The first part (feature marking component 701A) is arranged at intervals on the first (front) side of the door component 702, and the second part (feature marking component 701B) is arranged at intervals on the second (back) side of the door component 702. This arrangement provides comprehensive visual features, ensuring sufficient visual information for processing whether the robot approaches the electric door from the front and prepares to pass through, or whether the status of the door component 702 needs to be monitored during passage.

[0159] In practical applications, the first part of the feature identification component 701A can be arranged on the first surface of the door component 702 at the same interval, or at different intervals; similarly, the second part of the feature identification component 701B can be arranged on the second surface of the door component 702 at the same interval, or at different intervals. The interval can be any suitable range, and this embodiment does not limit this.

[0160] In one embodiment, the position of the feature marking component 701 on the first surface is the same as the position of the feature marking component 701 on the second surface relative to the door component 702.

[0161] In another embodiment, the position of the feature marking component 701 on the first surface is different from the position of the feature marking component 701 on the second surface relative to the door component 702.

[0162] In practical applications, the positions of the feature marking components 701 on the first surface and the feature marking components 701 on the second surface are the same relative to the door component 702. That is, the spacing between the first part of the feature marking components 701A when they are spaced apart on the first surface of the door component 702 can be the same as the spacing between the second part of the feature marking components 701B when they are spaced apart on the second surface of the door component 702. Alternatively, the positions of the feature marking components 701 on the first surface and the feature marking components 701 on the second surface are different relative to the door component 702. That is, the spacing between the first part of the feature marking components 701A when they are spaced apart on the first surface of the door component 702 can be different from the spacing between the second part of the feature marking components 701B when they are spaced apart on the second surface of the door component 702.

[0163] For example, if the feature identification component 701 is "L"-shaped, and the length of both sides of each "L"-shaped feature identification component 701 is 5cm, and the interval distance is set to a range of [10cm, 15cm], then the first part of the feature identification component 701A can be arranged on the first side of the door component 702 with the same interval distance (e.g., the horizontal and vertical intervals are both 12cm) selected from this range, or with different interval distances (e.g., the horizontal interval is 10cm and the vertical interval is 15cm) selected from this range; similarly, the second part of the feature identification component 701B can be arranged on the second side of the door component 702 with the same interval distance (e.g., the horizontal and vertical intervals are both 12cm) selected from this range, or with different interval distances (e.g., the horizontal interval is 12cm and the vertical interval is 14cm) selected from this range.

[0164] In practical applications, the number of feature identifiers included in the first feature identifier component 701A may be the same as the number of feature identifiers included in the second feature identifier component 701B; or, the number of feature identifiers included in the first feature identifier component 701A may be different from the number of feature identifiers included in the second feature identifier component 701B.

[0165] For example, if the number of multiple feature identification components 701 is 20, then the first part feature identification component 701A and the second part feature identification component 701B may each contain 10 feature identification components; or, the first part feature identification component 701A may contain 12 feature identification components and the second part feature identification component 701B may contain 8 feature identification components.

[0166] In one embodiment, the first part of the feature identification component 701A is symmetrically distributed about the vertical center line of the door component 702, and the second part of the feature identification component 701B is symmetrically distributed about the vertical center line of the door component 702.

[0167] In practical applications, both the first part of the feature identification component 701A and the second part of the feature identification component 701B can be symmetrically distributed about the vertical center line of the door component 702. That is, the first part of the feature identification component 701A has the same number of feature identification components on both sides of the vertical center line of the first surface of the door component 702, and they are symmetrically arranged. Similarly, the second part of the feature identification component 701B has the same number of feature identification components on both sides of the vertical center line of the second surface of the door component 702, and they are symmetrically arranged. This symmetrical layout helps to quickly determine the center position and orientation of the electric door in image processing, simplifying computational complexity and improving detection efficiency.

[0168] It should be noted that when the electric door includes multiple feature marking components 701, neither the first feature marking component 701A nor the second feature marking component 701B will be located on the vertical center line of the door body component 702.

[0169] For example, if the first part of the feature identification component 701A contains 12 feature identification components, then the first part of the feature identification component 701A has 6 feature identification components on both sides of the vertical center line of the first side of the door component 702 and they are arranged symmetrically. Similarly, if the second part of the feature identification component 701B contains 8 feature identification components, then the second part of the feature identification component 701B has 4 feature identification components on both sides of the vertical center line of the second side of the door component 702 and they are arranged symmetrically.

[0170] In one embodiment, the feature marking component 701 includes marking points with a radius greater than 3 millimeters (mm).

[0171] In practical applications, the radius of the marking points included in the feature marking component 701 is greater than 3mm. Thus, when the robot is 0.1m to 2.5m away from the electric door, the effective acquisition angle of the sensors in the robot is 120°, including an effective vertical field of view and / or an effective horizontal field of view of 120° (the specific angle depends on the type of sensor). This means the robot can effectively identify the marking points on the door within a 120-degree field of view in the vertical and / or horizontal planes, thereby accurately identifying the position of the electric door. Furthermore, when the robot is 0.1m to 2.5m away from the electric door, it can also effectively adjust the posture of its vehicle body.

[0172] It should be noted that the above-mentioned effective collection angles are those from which the confidence level of the collected data reaches 80% or higher.

[0173] It should be noted that if the radius of the marker is less than 3mm, the marker is too small and the robot cannot effectively identify the marker when it is 2.5m away from the electric gate. As a result, the robot needs to move closer to the electric gate to identify the marker. When the distance is too close, the robot's body adjustment posture will be restricted.

[0174] In one embodiment, the feature marking component 701 includes at least three marking points whose circumscribed circle has a radius greater than 5 cm.

[0175] In practical applications, at least three of the marking points in the feature marking component 701 form a circumscribed circle with a radius greater than 5cm. Thus, when the robot is 0.1m to 2.5m away from the electric door, the effective acquisition angle of the sensors in the robot is 120°, including an effective vertical field of view and / or an effective horizontal field of view of 120° (the specific angle depends on the type of sensor). This means the robot can effectively identify the marking points on the door within a 120-degree field of view in the vertical and / or horizontal planes, thereby accurately identifying the position of the electric door. The effective acquisition angle is defined as the acquisition angle with a confidence level of 80% or higher.

[0176] It should be noted that if the radius of the circumcircle formed by three of the markers is less than 5cm, the robot needs to be closer to the electric gate to recognize the markers. When the distance is too close, the robot's body adjustment posture will be restricted.

[0177] In one embodiment, the feature marking component 701 includes at least three marking points whose circumscribed circle has a radius of less than 30 cm.

[0178] In practical applications, at least three of the marking points in the feature marking component 701 form a circumscribed circle with a radius less than 30cm. Thus, when the robot is 0.1m to 2.5m away from the electric door, the effective acquisition angle of the robot's sensors is 120°, including an effective vertical field of view and / or an effective horizontal field of view of 120° (the specific angle depends on the type of sensor). This means the robot can effectively identify the marking points on the door within a 120-degree field of view in the vertical and / or horizontal planes, thereby accurately identifying the position of the electric door. The effective acquisition angle is defined as the acquisition angle with a confidence level of 80% or higher.

[0179] It should be noted that if the radius of the circumcircle formed by three of the marker points is greater than 30cm, the three marker points may be within the robot's detection range. The robot cannot effectively identify the marker points and therefore cannot determine the position or posture of the electric gate based on the marker points.

[0180] In one embodiment, the maximum circumscribed shape corresponding to the first feature identifier 701A and the second feature identifier 701B is a rectangle, and the radius of the maximum circumscribed circle corresponding to the rectangle is greater than or equal to 5cm and less than or equal to 30cm.

[0181] In practical applications, the maximum circumscribed shapes corresponding to the first feature identification component 701A and the second feature identification component 701B are both rectangles. That is, the first feature identification component 701A is located within the first rectangle on the first surface of the door component 702, and the second feature identification component 701B is located within the second rectangle on the second surface of the door component 702. Furthermore, the radius of the maximum circumscribed circle corresponding to the first rectangle is greater than or equal to 5cm and less than 30cm, and the radius of the maximum circumscribed circle corresponding to the second rectangle is greater than or equal to 5cm and less than or equal to 30cm. Thus, when the robot is 0.1m away from the electric door, the effective acquisition angle of the sensors in the robot is 120°, including an effective vertical field of view and / or an effective horizontal field of view of 120° (the specific angle depends on the type of sensor). This means the robot can effectively identify the markings on the door within a 120-degree field of view in the vertical and / or horizontal planes, thereby accurately locating the electric door. The effective acquisition angle is defined as the acquisition angle with a confidence level of 80% or higher.

[0182] It should be noted that the first rectangle can be the same as the second rectangle, or it can be different from the second rectangle. In other words, the first rectangle can be the same as the second rectangle if all of the following conditions are met; otherwise, they are different. These conditions include:

[0183] (1) The spacing between the first part of the feature identification component 701A when it is arranged at intervals on the first side of the door component 702 is the same as the spacing between the second part of the feature identification component 701B when it is arranged at intervals on the second side of the door component 702.

[0184] (2) The number of feature identification components contained in the first part 701A is the same as the number of feature identification components contained in the second part 701B.

[0185] (3) The first part of the feature identification component 701A has the same number of feature identification components on both sides of the vertical center line of the first side of the door component 702 and is arranged symmetrically. The second part of the feature identification component 701B has the same number of feature identification components on both sides of the vertical center line of the second side of the door component 702 and is arranged symmetrically.

[0186] For example, if the first part of the feature identification component 701A and the second part of the feature identification component 701B each contain 4 feature identification components, and the first part of the feature identification component 701A is arranged at intervals of 10cm on the first surface of the door component 702 (both horizontal and vertical intervals are 10cm), and the second part of the feature identification component 701B is arranged at intervals of 10cm on the second surface of the door component 702 (both horizontal and vertical intervals are 10cm), and both the first part of the feature identification component 701A and the second part of the feature identification component 701B are symmetrically distributed about the vertical center line of the door component 702, then the first rectangular area of ​​the first part of the feature identification component 701A on the first surface of the door component 702 is the same as the second rectangular area of ​​the second part of the feature identification component 701B on the second surface of the door component 702, that is, the first rectangle and the second rectangle are the same.

[0187] In one embodiment, the feature identifier 701 has a length of 5cm, a width of 6mm, and a height of 5cm.

[0188] In practical applications, each feature identification component 701 in the electric gate has a length of 5cm, a width of 6mm, and a height of 5cm. Thus, while ensuring the dimensions of each feature identification component 701 are within a suitable range, the effective acquisition angle of the robot's sensors is 120°, including an effective vertical field of view and / or an effective horizontal field of view of 120° (the specific angle depends on the type of sensor). This allows the robot to effectively identify the feature identification component 701 within a 120-degree field of view in the vertical and / or horizontal planes, thereby enabling precise positioning of the electric gate. The effective acquisition angle is defined as the acquisition angle with a confidence level of 80% or higher.

[0189] In one embodiment, such as Figure 9 As shown, the electric gate includes multiple feature marking components 701. The multiple feature marking components 701 are divided into a first type of feature marking component 701C and a second type of feature marking component 701D according to their arrangement height on the gate body component 702. The height of the first type of feature marking component 701C is greater than the height of the second type of feature marking component 701D.

[0190] In practical applications, the multiple feature identification components 701 are set at different heights. These feature identification components 701 are divided into a first type of feature identification component 701C and a second type of feature identification component 701D according to their placement height on the door component 702. The first type of feature identification component 701C is the upper feature identification, and the second type of feature identification component 701D is the lower feature identification. That is, the height of the first type of feature identification component 701C is greater than the height of the second type of feature identification component 701D. All heights are assumed to be above the ground.

[0191] In one embodiment, the height of the second type of feature identification component 701D is less than the height of the horizontal centerline of the door component 702; and / or, the height of the first type of feature identification component 701C is greater than the height of the recognition sensor in the robot; and / or, the height of the second type of feature identification component 701D is less than the height of the recognition sensor in the robot.

[0192] In practical applications, the height of the second type of feature marker component 701D is lower than the height of the horizontal centerline of the door component 702, the height of the first type of feature marker component 701C is higher than the height of the recognition sensor in the robot, and the height of the second type of feature marker component 701D is lower than the height of the recognition sensor in the robot. In other words, the lower feature marker must be lower than the horizontal centerline of the door component 702, the upper feature marker must be higher than the recognition sensor in the robot, and the lower feature marker must be lower than the recognition sensor in the robot. This height-matching layout allows the robot to obtain effective visual features from different heights and perspectives, thereby increasing the robustness of detection, especially in complex terrain or with a certain slope, enabling the robot to better adapt to different observation angles.

[0193] It should be noted that since multiple feature marking components 701 are arranged on the front and back of the door component 702, both the front and back of the door component 702 include upper and lower feature markings. That is, both the first part of feature marking component 701A and the second part of feature marking component 701B include upper and lower feature markings. The first part of feature marking component 701A includes the corresponding front first type feature marking component 701AC and front second type feature marking component 701AD. The second part of feature marking component 701B includes the corresponding back first type feature marking component 701BC and back second type feature marking component 701BD.

[0194] Among them, the height of the front first type feature identification component 701AC and the back first type feature identification component 701BC is greater than the height of the recognition sensor in the robot, the height of the front second type feature identification component 701AD and the back second type feature identification component 701BD is less than the height of the recognition sensor in the robot, and the height of the front second type feature identification component 701AD and the back second type feature identification component 701BD is less than the height of the horizontal centerline of the door component 702.

[0195] In one embodiment, such as Figure 10 As shown, the door component 702 includes two door bodies 1001 and 1002; wherein, the two door bodies 1001 and 1002 have a double door structure, and each of the two door bodies 1001 and 1002 is provided with a feature identification component 701.

[0196] In practical applications, door component 702 adopts a double-door structure, meaning that door component 702 includes door body 1001 and door body 1002. Door body 1001 is located on the left side of door component 702, and door body 1002 is located on the right side of door component 702. Door bodies 1001 and 1002 are symmetrically arranged about the vertical center line of door component 702, and feature identification components 701 are provided on both the front and back sides of door bodies 1001 and 1002. That is, the first part of the feature identification components 701A is symmetrically arranged about the first side of door bodies 1001 and 1002, and the second part of the feature identification components 701B is symmetrically arranged about the second side of door bodies 1001 and 1002.

[0197] For example, if the first part of the feature identification component 701A and the second part of the feature identification component 701B each contain 4 feature identification components, then the first part of the feature identification component 701A has 2 feature identification components on the first surface of the door body 1001 and the door body 1002, and they are arranged symmetrically. The second part of the feature identification component 701B has 2 feature identification components on the second surface of the door body 1001 and the door body 1002, and they are arranged symmetrically.

[0198] In one embodiment, the door component 702 further includes a door frame and a connecting structure, the connecting structure being connected to the door frame and fixed to the fence.

[0199] In one embodiment, such as Figure 11 As shown, both door body 1001 and door body 1002 are provided with multiple air holes 1100, and the multiple air holes 1100 are symmetrically arranged about door body 1001 and door body 1002.

[0200] In one embodiment, such as Figure 12As shown, the door component 702 may also include a sub-door 1201 and a sub-door 1202, that is, the door 1001 and the door 1002 can respectively nest the sub-door 1201 and the sub-door 1202. The sub-door 1201 and the sub-door 1202 form a double door structure. The sub-door 1201 is located on the right side of the door 1001, and the sub-door 1202 is located on the left side of the door 1002. Feature marking components 701 are provided on both the front and back of the sub-door 1201 and the sub-door 1202 and are symmetrically distributed.

[0201] It should be noted that if the robot's height is less than or equal to the second preset height, when the robot approaches from the front and prepares to pass through the electric gate, only sub-gate 1201 and sub-gate 1202 need to be opened. If the robot's height is greater than the second preset height, when the robot approaches from the front and prepares to pass through the electric gate, gate 1001 and gate 1002 will also be opened. Opening gate 1001 and gate 1002 will simultaneously open sub-gate 1201 and sub-gate 1202. This allows for better adaptation to robots of different heights.

[0202] It should be noted that, in order to prevent the feature identification component 701 from being obstructed, the height of the side support feet of the door component 702 can be set so that the feature identification component 701 cannot be obstructed within the 120° fan-shaped area in front of the door component 702. This ensures that the feature identification component 701 can always be clearly captured by the recognition sensor on the robot within the common angle range when the robot approaches the electric door, avoiding the impact on detection accuracy and efficiency due to obstruction by the side structure.

[0203] The electric gate provided in this application embodiment includes one or more feature identification components and a gate body component. The feature identification components are disposed on the gate body component and include identification points. The identification points include one or more of the following: corner points and / or endpoints of the feature identification component shape; color difference points that distinguish the feature identification component from its surroundings; and material texture difference points of the feature identification component. The feature identification components are used for robot recognition. Thus, by optimizing the visual feature settings of the electric gate and placing one or more feature identification components on the gate body component, the robot can accurately and efficiently identify the electric gate within a more flexible angular range. Furthermore, the multiple feature identification components include identification points, which include corner points and / or endpoints of the feature identification component shape, and / or color difference points that distinguish the feature identification component from its surroundings, and / or material texture difference points of the feature identification component. Due to the prominent visual features of the identification points, they can be quickly recognized by the robot, thereby enabling the robot to accurately locate the electric gate from a greater distance and accurately determine the relative pose between the robot and the electric gate. Therefore, the technical solution of this application has stronger robustness to complex terrain and can improve the accuracy and reliability of the robot's autonomous operation.

[0204] This application embodiment also proposes a feature identification component, which includes identification points, and the identification points include one or more of the following:

[0205] Features identify the corners and / or endpoints of the component shape;

[0206] Distinguishing features from the color differences around the components that are marked with distinctive markings;

[0207] Featured components highlight differences in material texture;

[0208] The feature identification component is used for robot recognition.

[0209] It should be noted that, in addition to being installed on the door body components of the aforementioned electric gate, the feature marking components can also be installed on the passageway structure or other markers. The passageway structure refers to the internal passageway design of the electric gate or the passageways between door bodies. The markers can be flags, models, or other objects with distinctive features, and these markers can be installed independently on the electric gate.

[0210] In one embodiment, the feature identification component includes more than three identification points in total.

[0211] In one embodiment, the feature identification component includes more than three identification points, and at least three of the identification points are located at a height greater than 10cm.

[0212] In one embodiment, the feature identification component includes more than three identification points, and at least three of the identification points are located at a height of not less than 30cm.

[0213] In one embodiment, the feature marking component includes marking points with a radius greater than 3 mm.

[0214] In one embodiment, the feature marking component includes at least three marking points whose circumscribed circle has a radius greater than 5 cm.

[0215] In one embodiment, the feature marking component includes at least three marking points whose circumscribed circle has a radius of less than 30 cm.

[0216] In one embodiment, the maximum circumscribed shape corresponding to the feature identifier is a rectangle, and the radius of the maximum circumscribed circle corresponding to the rectangle is greater than or equal to 5cm and less than or equal to 30cm.

[0217] In one embodiment, the feature identifier has a length of 5cm, a width of 6mm, and a height of 5cm.

[0218] This application also proposes an electric gate positioning method for use in robots. Specifically, the robot can be a lawnmower, which can be an intelligent lawnmower, comprising several main parts such as an identification sensor, a navigation and positioning device, and a moving device. Figure 13 This is a flowchart illustrating the electric door positioning method provided in an embodiment of this application, as shown below. Figure 13 As shown, the method includes the following steps:

[0219] Step 1301: Inspect the feature marking components on the electric gate.

[0220] The electric gate includes one or more feature identification components and a gate body component. Multiple feature identification components are disposed on the gate body component. The feature identification components include identification points, which include one or more of the following: corner points and / or endpoints of the feature identification component shape; color difference points that distinguish the feature identification component from its surroundings; and material texture difference points of the feature identification component.

[0221] In this embodiment, the robot's recognition sensors can perform feature detection on the electric gate to obtain one or more feature identification components on the gate. These feature identification components can be spaced apart on the gate components, and the spacing between them can be any suitable range; this embodiment does not limit this. This avoids feature confusion caused by overly concentrated feature identification components, while also ensuring that the robot's recognition sensors can capture multiple identifiable key points at different distances and angles, thus improving detection accuracy.

[0222] In one embodiment, step 1301 may specifically include:

[0223] Images of the electric gate are acquired by an identification sensor, and one or more feature markers in the images are identified.

[0224] In practical applications, the robot can first acquire a two-dimensional (2D) image of the electric gate through the recognition sensor, and then use computer vision technology to perform target detection on the 2D image of the electric gate through the recognition sensor to obtain one or more feature identification components included in the 2D image, that is, one or more feature identification components on the electric gate.

[0225] In practical applications, object detection technology may include one or more of the following algorithms: You Once Look Once (YOLO), Region-based Convolutional Neural Networks (R-CNN), etc. This application does not limit the specific algorithms used.

[0226] Step 1302: Determine the position information of the electric gate based on the feature identification component.

[0227] In this embodiment, after detecting one or more feature markers on the electric gate, the position information of the electric gate can be determined based on the position information of each of the one or more feature markers. That is, the position information of the electric gate includes the position information of one or more feature markers, which includes the pixel coordinates of each feature marker in the 2D image and its position coordinates in three-dimensional space.

[0228] In one embodiment, step 1302 may specifically include:

[0229] Each feature identifier component in one or more feature identifier components is detected for identifier points to obtain multiple identifier points;

[0230] Based on the pixel coordinates and position coordinates of each of the multiple marker points, the position information of one or more feature marker components is determined.

[0231] In practical applications, the robot's recognition sensors first detect marking points for each feature component, resulting in multiple marking points. These marking points can be corners and / or endpoints of the feature component's shape, and / or color difference points around the feature component, and / or material texture difference points. Corners, or extreme points, are points within the feature component with local maximum curvature or significant gradient changes. Endpoints are edge points of the feature component. Color difference points are points with significant color differences from the surrounding area of ​​the feature component. Material texture points are points with significant material and texture differences from the surrounding area of ​​the feature component. Then, based on the intrinsic and extrinsic parameters of the recognition sensors and the pixel coordinates of each marking point in the 2D image for each feature component, the actual position coordinates of each marking point in 3D space are determined. Finally, the average pixel coordinates of each marking point in the 2D image are taken as the pixel coordinates of the corresponding feature component in the 2D image, and the average actual position coordinates of each marking point in 3D space are taken as the position coordinates of the corresponding feature component in 3D space, thereby determining the position information of one or more feature components.

[0232] In practical applications, the actual position coordinates of each marker point in three-dimensional space can be determined as follows: the intrinsic parameter information (focal length, principal point coordinates, etc.) and extrinsic parameter information (rotation matrix and translation vector) of the recognition sensor, such as the camera, are obtained through camera calibration methods (such as Zhang Zhengyou calibration method). Then, using the extrinsic and intrinsic parameter information of the camera, the pixel coordinates of each marker point in the 2D image are converted into the actual position coordinates in three-dimensional space.

[0233] In practical applications, the marker detection algorithm may include one or more of other algorithms such as Scale-invariant feature transform (SIFT) and Oriented Fast and Rotated BRIEF (ORB), and this application embodiment does not limit this.

[0234] Step 1303: Determine the relative pose between the robot and the electric gate based on the position information of the electric gate.

[0235] In this embodiment, after obtaining the position information of the electric door, a pose estimation algorithm can be used to determine the relative pose between the robot and the electric door by combining the pixel coordinates of the electric door in the 2D image and its position coordinates in three-dimensional space. This enables the robot to clearly understand its relative positional relationship with the electric door, thereby achieving accurate positioning of the electric door. The relative pose includes the rotation matrix and translation vector of the robot relative to the electric door.

[0236] In one embodiment, step 1303 may specifically include:

[0237] Based on the position information of one or more feature-identified components and the distance between the electric gate and the robot, the relative pose between the electric gate and the robot is determined.

[0238] In practical applications, the distance between the robot and the electric gate can be calculated in real time using the robot's recognition sensors or navigation and positioning devices. Then, a pose estimation algorithm is used, combining the position information of one or more feature markers and the distance information between the electric gate and the robot, to calculate the pose of the electric gate relative to the robot. Specifically, a projection model including a rotation matrix and a translation vector can be constructed based on the pixel coordinates of each feature marker in the 2D image and its position coordinates in 3D space, the distance between the electric gate and the robot, and the intrinsic parameter information of the recognition sensors. The translation vector is then decomposed into direction and magnitude (known distance). Based on the projection model, direction and magnitude, and the position coordinates of each feature marker in 3D space, a projection error function for one or more feature markers is defined. The rotation matrix and direction in the projection error function are then iteratively optimized to obtain the target rotation matrix and target translation vector. Thus, the pose of the electric gate relative to the robot is determined based on the target rotation matrix and target translation vector.

[0239] In practical applications, the pose estimation algorithm may include one or more other algorithms such as the Perspective-n-Point (PnP) algorithm, and the embodiments of this application do not limit this.

[0240] In the technical solution provided in this application embodiment, the robot detects the feature marking components on the electric door and determines the position information of the electric door based on the feature marking components, thereby determining the relative pose between the robot and the electric door based on the position information of the electric door; wherein, the electric door includes one or more feature marking components and a door body component, the feature marking components are disposed on the door body component, and the feature marking components include marking points, the marking points including one or more of the following: corner points and / or endpoints of the shape of the feature marking components; color difference points that distinguish the feature marking components from the surrounding area; and material texture difference points of the feature marking components. Thus, by optimizing the visual feature settings of the electric gate and placing one or more feature markers on the gate components, the robot can accurately and efficiently identify the electric gate within a more flexible angular range. The feature markers include marker points, which include corner points and / or endpoints of the feature marker shape, and / or color difference points that distinguish the feature marker from its surroundings, and / or material texture difference points. Due to the prominent visual features of the marker points, they can be quickly identified by the robot, enabling the robot to accurately locate the electric gate from a greater distance and precisely determine the relative pose between the robot and the electric gate based on the gate's position information. Therefore, the technical solution of this application has stronger robustness to complex terrain and can improve the accuracy and reliability of the robot's autonomous operation.

[0241] This application also provides an electric gate for a lawnmower and a related detection and positioning method. Figure 14 This is a schematic diagram of the structure of the electric gate for a lawnmower provided in an embodiment of this application, as shown below. Figure 14 As shown, the lawnmower's electric gate innovates in its visual features by setting four "L"-shaped reflective strips on both the front and back of the gate as visual identifiers.

[0242] The lawnmower uses its onboard camera (i.e., the aforementioned recognition sensor 101) to capture 2D images of the electric gate. Employing deep learning methods for target detection and keypoint detection, it detects the corners and endpoints of each "L"-shaped reflective strip in the captured 2D image, using these as keypoints. Then, combining the actual position and distance of each "L"-shaped reflective strip, the relative pose between the lawnmower and the electric gate is calculated in real-time using the PnP algorithm. This enables the lawnmower to accurately identify and position itself within the electric gate, allowing for more efficient and stable passage.

[0243] Specifically, the above process can be divided into the following technical points:

[0244] (1) Number and position of reflective strips

[0245] Four L-shaped reflective strips are installed on both the front and back of the electric gate. This double-sided arrangement ensures sufficient visual features for the lawnmower to detect the machine in real time within a 150° fan-shaped area in front of the gate. Even if there is some obstruction on one side at a certain angle, the reflective strips on the other side can still provide effective information, greatly improving the reliability of detection.

[0246] (2) Key point detection

[0247] A 2D image of the front of the electric gate was captured using a camera mounted on a lawnmower. Deep learning methods for object detection and keypoint detection were employed to detect corner points and endpoints in each "L"-shaped reflective strip in the captured 2D image. Each "L"-shaped reflective strip includes one corner point and two endpoints; therefore, four "L"-shaped reflective strips contain a total of four corner points and eight endpoints, or 12 keypoints (feature markers). The deep learning algorithm accurately extracted these key feature markers in complex environmental backgrounds, providing foundational data for subsequent pose calculations.

[0248] (3) Pose calculation based on PnP algorithm

[0249] After detecting 12 key points, the PnP algorithm is used to calculate the relative pose between the lawnmower and the electric gate in real time, combining the actual position of each "L"-shaped reflective strip on the electric gate and the distance information between each "L"-shaped reflective strip and the lawnmower. Specifically, the PnP algorithm can solve for the pose and position of the camera on the lawnmower relative to the electric gate based on the pixel coordinates of the 12 key points in the 2D image and the actual positional relationship of the 12 key points in three-dimensional space. This allows the lawnmower to clearly understand its relative positional relationship with the electric gate and achieve precise positioning of the electric gate.

[0250] (4) Optimization of reflective strip layout

[0251] 1) Spacing setting: Multiple "L"-shaped reflective strips are distributed at intervals to avoid being too concentrated and causing feature confusion. At the same time, it ensures that the camera can capture multiple identifiable key points at different distances and angles, thereby improving the accuracy of detection.

[0252] 2) Symmetrical arrangement: Multiple "L"-shaped reflective strips are symmetrically distributed about the vertical center line of the gate. This symmetrical layout helps to quickly determine the center position and orientation of the electric gate in image processing, simplifying algorithm complexity and improving detection efficiency.

[0253] 3) Height Distribution: Multiple "L"-shaped reflective strips are positioned at varying heights, with upper and lower feature markers on the gate. The upper feature marker is higher than the gate's horizontal marker, while the lower feature marker is lower than the gate's horizontal center line. The upper feature marker is higher than the height of the recognition sensor on the lawnmower, while the lower feature marker is lower than the height of the camera on the lawnmower. This height-distribution layout allows the lawnmower to acquire effective visual features from different heights, increasing detection robustness, especially in complex terrain or on slopes, better adapting to different observation angles. Furthermore, setting the lowest reflective strip below the height of the lawnmower's camera plays a crucial role in addressing the problem of tall grass obstructing the view. Tall grass is a common disturbance in lawns and can easily hinder the lawnmower's detection of the motorized gate. Because tall grass grows upwards from the ground, the lowest reflective strip is less likely to be obstructed than the higher reflective strips, making it easier for the lawnmower's camera to capture some of its features even in dense tall grass. By combining deep learning technologies for object detection and key point detection, the camera on the lawnmower can extract key features from complex backgrounds containing tall grass, and calculate the relative pose between the lawnmower and the electric gate using the PnP algorithm. This ensures that the lawnmower can still accurately identify the electric gate even in tall grass environments, significantly enhancing the adaptability and reliability of detection in complex grassland environments. Even different models of lawnmowers (with different camera heights) can recognize some identification marks.

[0254] 4) Avoid collinear arrangement: Multiple "L"-shaped reflective strips are not collinear in a plane parallel to the door. This layout ensures that the features formed by the reflective strips are unique when observed from any angle, avoiding misjudgment or information loss due to collinearity, and further improving the accuracy and reliability of detection.

[0255] It should be noted that the height of a typical lawn may reach 10cm. To ensure that the reflective strips are not obscured by the lawn and can be detected by the lawnmower's recognition sensors, at least three of the key points included in the multiple "L"-shaped reflective strips must be non-collinear and have a height greater than 10cm from the ground.

[0256] For example, to ensure the highest recognition accuracy while addressing the occlusion problem caused by grass and other objects less than 13cm in height, the lowest point of all key points included in the reflective strip on the electric gate can be set to be 13cm above the ground; or, to address the occlusion problem caused by grass and other objects less than 34cm in height, at least three non-collinear points of all key points included in the reflective strip on the electric gate can be set to be at least 34cm above the ground.

[0257] (5) Combination of door structure and reflective strips

[0258] 1) Double-door structure: The gate adopts a double-door structure, which includes two sub-gates, each equipped with an "L"-shaped reflective strip. This not only adapts to common electric gate structures, but also allows the lawnmower to obtain the gate's status and position information by detecting the reflective strips when passing through the gate, regardless of whether the double doors are open or closed, thus enhancing adaptability to different working scenarios.

[0259] 2) Full coverage: The front and back of the gate are equipped with "L"-shaped reflective strips, providing visual features from all directions. Whether the lawnmower approaches from the front and is about to pass through the electric gate, or the status of the gate needs to be monitored during the passage of the electric gate, there is sufficient visual information for processing.

[0260] (6) Other auxiliary designs

[0261] 1) Prevent obstruction: The height of the side support legs of the gate should not obstruct the reflective strip within a 120° fan-shaped area in front of the gate. This ensures that the reflective strip can always be clearly captured by the camera within the common angle range when the lawnmower approaches the electric gate, avoiding the impact of detection due to obstruction by the side structure.

[0262] 2) Material Selection: The reflective strip should ideally be made of a frosted material to prevent excessive white reflection from interfering with detection under direct sunlight or other conditions. A frosted material ensures good reflectivity while effectively reducing interference from reflections, thus improving detection stability.

[0263] The technical solution of this application innovates in the visual feature setting of the electric gate. Specifically, four "L"-shaped reflective strips are set on both the front and back of the electric gate as visual feature markers. The lawnmower uses its own camera and deep learning technology of target detection and key point detection to detect the corner points and endpoints contained in each "L"-shaped reflective strip in the acquired 2D image, and uses them as 12 key points. Then, with the help of the PnP algorithm, combined with information such as the real position and distance of the "L"-shaped reflective strips, the relative pose of the lawnmower and the electric gate is calculated in real time with high accuracy. This enables the lawnmower to accurately identify and locate the electric gate, so as to pass through the electric gate more efficiently and stably.

[0264] This application also provides an electric gate positioning device for use with a robot. Specifically, the robot can be a lawnmower, and the lawnmower can be an intelligent lawnmower. It includes several major parts such as an identification sensor, a navigation and positioning device, and a moving device. Figure 15 This is a schematic diagram of the electric door positioning device provided in the embodiments of this application, as shown below. Figure 15 As shown, the device includes:

[0265] The detection unit 1501 is used to detect the feature marking components on the electric gate; wherein the electric gate includes one or more feature marking components and a gate body component, the feature marking components are disposed on the gate body component, and the feature marking components include marking points, the marking points including one or more of the following: corner points and / or endpoints of the shape of the feature marking component; color difference points that are different from the surrounding area of ​​the feature marking component; material texture difference points of the feature marking component.

[0266] The determining unit 1502 is used to determine the position information of the electric gate based on the feature identification component; and to determine the relative pose between the robot and the electric gate based on the position information of the electric gate.

[0267] In one embodiment, the detection unit 1501 is specifically used to acquire an image of the electric gate through an identification sensor and identify one or more feature markers in the image.

[0268] In one embodiment, the position information of the electric gate includes the position information of one or more feature identification components; wherein,

[0269] The determining unit 1502 is specifically used to perform marker point detection on each of the one or more feature marker components to obtain multiple marker points; and to determine the position information of the one or more feature marker components based on the pixel coordinates and position coordinates corresponding to each marker point among the multiple marker points.

[0270] In one embodiment, the determining unit 1502 is further configured to determine the relative pose between the electric gate and the robot based on the position information of one or more feature identification components and the distance between the electric gate and the robot.

[0271] In the technical solution provided in this application embodiment, the robot detects the feature marking components on the electric door and determines the position information of the electric door based on the feature marking components, thereby determining the relative pose between the robot and the electric door based on the position information of the electric door; wherein, the electric door includes one or more feature marking components and a door body component, the feature marking components are disposed on the door body component, and the feature marking components include marking points, the marking points including one or more of the following: corner points and / or endpoints of the shape of the feature marking components; color difference points that distinguish the feature marking components from the surrounding area; and material texture difference points of the feature marking components. Thus, by optimizing the visual feature settings of the electric gate and placing one or more feature markers on the gate components, the robot can accurately and efficiently identify the electric gate within a more flexible angular range. The feature markers include marker points, which include corner points and / or endpoints of the feature marker shape, and / or color difference points that distinguish the feature marker from its surroundings, and / or material texture difference points. Due to the prominent visual features of the marker points, they can be quickly identified by the robot, enabling the robot to accurately locate the electric gate from a greater distance and precisely determine the relative pose between the robot and the electric gate based on the gate's position information. Therefore, the technical solution of this application has stronger robustness to complex terrain and can improve the accuracy and reliability of the robot's autonomous operation.

[0272] Those skilled in the art should understand that Figure 15 The functions of each unit in the electric door positioning device shown can be understood by referring to the relevant descriptions of the aforementioned method. Figure 15 The functions of each unit in the electric door positioning device shown can be realized by a program running on a processor or by a specific logic circuit.

[0273] The robot and electric gate provided in this application embodiment include: a recognition sensor, a detection module, a first interaction module, and a first control module; wherein, the detection module is used to determine the position of the target electric gate using the recognition sensor; the first interaction module is used to send a first command to the target electric gate, the first command being used to control the target electric gate to open; the first control module is used to adjust the robot's posture based on the position of the target electric gate, so as to control the robot to pass through the target electric gate. The solution provided in this application embodiment, by setting a recognition sensor on the robot, enables the robot to have the ability to recognize (i.e., detect) electric gates. When the robot needs to pass through a specific electric gate (i.e., the target electric gate), it can use the recognition sensor to determine the position of the electric gate, control the electric gate to open, and automatically pass through the electric gate based on the position. Thus, the accuracy of the robot's electric gate position detection can be effectively improved through the recognition sensor, and the robot can automatically pass through the electric gate without increasing the cost of the electric gate, eliminating the need for the user to manually open the electric gate. This significantly improves the robot's intelligence level and reduces the complexity of user operation, thereby enhancing the user experience.

[0274] In addition, the solution provided in this application supports the "one vehicle, multiple doors" scenario and the "one door, multiple vehicles" scenario, that is, a robot can establish a binding relationship (i.e., association relationship) with one or more electric doors, and an electric door can establish a binding relationship with one or more robots; thus, it can cover various deployment needs of users, such as situations where multiple electric doors need to be installed at home or multiple robots need to work at the same time.

[0275] Furthermore, the solution provided in this application allows the robot to detect the surrounding environment of the electric gate and determine the opening and closing opportunities. For example, when a fixed obstacle is detected, the robot can control the electric gate to open and intelligently avoid obstacles using a preset specific strategy. Alternatively, it can push the obstacle aside before continuing through the electric gate. When a target animal (such as a user's pet, specifically a cat or dog) is detected, the robot can temporarily refrain from controlling the electric gate to open and play a specific audio clip at maximum volume to scare away the target animal. This prevents the user's pet from running outside while the electric gate is open, reducing the risk of the pet getting lost and improving the user experience. As another example, when the robot determines that it has successfully passed through the electric gate, it can issue a closing command to the electric gate, thereby closing the electric gate in a timely manner and also reducing the risk of the pet getting lost, further improving the user experience.

[0276] In addition, the solution provided in this application embodiment allows the robot to proactively check the working / fault status of the electric door by obtaining data such as power consumption and logs from the electric door, and promptly provide feedback to the user or the electric door, thereby enabling timely repair and adjustment of the electric door and improving the user experience.

[0277] Furthermore, the solution provided in this application, by optimizing the visual feature settings of the electric door and placing one or more feature identification components on the door body components, enables the robot to accurately and efficiently identify the electric door within a more flexible angular range. The multiple feature identification components include identification points, which include corner points and / or endpoints of the feature identification component's shape, and / or color difference points distinguishing it from the surrounding area, and / or material texture difference points. Due to the prominent visual features of the identification points, they can be quickly identified by the robot, enabling the robot to accurately locate the electric door from a greater distance and precisely determine the relative pose between the robot and the electric door. Therefore, the technical solution of this application has stronger robustness to complex terrain and can improve the accuracy and reliability of the robot's autonomous operation.

[0278] Figure 16 This is a schematic diagram of the processing device provided in the embodiments of this application. Figure 16 The processing device shown includes a processor 1601, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0279] In one embodiment, such as Figure 16 As shown, the processing device may further include a memory 1602. The processor 1601 can retrieve and run computer programs from the memory 1602 to implement the methods described in the embodiments of this application.

[0280] The memory 1602 can be a separate device independent of the processor 1601, or it can be integrated into the processor 1601.

[0281] In one embodiment, such as Figure 16 As shown, the processing device may also include a transceiver 1603, which the processor 1601 can control to communicate with other devices. Specifically, it can send information or data to other devices or receive information or data sent by other devices.

[0282] The transceiver 1603 may include a transmitter and a receiver. The transceiver 1603 may further include an antenna, and the number of antennas may be one or more.

[0283] The processing device may specifically be a robot or an electric door as described in this application embodiment, and the processing device can implement the corresponding processes of the various methods implemented in this application embodiment. For the sake of brevity, it will not be described in detail here.

[0284] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0285] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0286] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0287] This application also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to the processing device in this application embodiment, and the computer program causes the computer to execute the corresponding processes implemented by the various methods in this application embodiment; for brevity, further details are omitted here.

[0288] This application also provides a computer program product, including computer program instructions. This computer program product can be applied to the processing device in this application embodiment, and the computer program instructions cause the computer to execute the corresponding processes implemented by the various methods in this application embodiment; for brevity, further details are omitted here.

[0289] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0290] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0291] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0292] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0293] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0294] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0295] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0296] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0297] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A robot, characterized in that, include: The system includes an identification sensor, a detection module, a first interaction module, and a first control module; wherein, The detection module is used to determine the position of the target electric door using the identification sensor; The first interaction module is used to send a first instruction to the target electric door, the first instruction being used to control the target electric door to open; The first control module is used to adjust the robot's posture based on the position of the target electric gate, so as to control the robot to pass through the target electric gate.

2. The robot of claim 1, wherein, The detection module is also used for: Using the identification sensor, identify points that are associated with the target electric gate; The position of the target electric gate is determined based on the detected marker points if one or more of the following conditions are met: One or more preset target markers were detected; The number of detected markers is greater than or equal to the first threshold.

3. The robot of claim 1, wherein, The detection module is also used to use the identification sensor to detect whether there are obstacles within a preset range that are related to the target electric door; The first interaction module is further configured to send the first instruction to the target electric door when the detection module detects that there is no obstacle within the preset range.

4. The robot of claim 3, wherein, The first control module is further configured to execute a corresponding processing strategy based on the type of obstacle when the detection module detects an obstacle within the preset range.

5. The robot of claim 4, wherein, The first control module is further configured to control the robot to perform a target operation when the obstacle includes a target animal, the target operation being used to drive away the target animal.

6. The robot according to any one of claims 1 to 5, characterized in that, The detection module is also used to detect whether the robot has successfully passed through the target electric gate using positioning technology; The first interaction module is further configured to send a second instruction to the target electric gate when the detection module detects that the robot has successfully passed through the target electric gate, the second instruction being used to control the target electric gate to close.

7. The robot according to any one of claims 1 to 5, characterized in that, The first interaction module is further configured to acquire first information of the target electric door, the first information including relevant information on the working status of the target electric door; The detection module is also used to perform fault detection on the target electric door based on the first information.

8. The robot according to any one of claims 1 to 5, characterized in that, The first interaction module is also used to actively or passively establish a communication connection with one or more electric doors, establish and store the association between the robot and the one or more electric doors, wherein the one or more electric doors include at least the target electric door.

9. An electrically operated door characterised in that, include: One or more feature identification components and a door body component, wherein the feature identification component is disposed on the door body component, and the feature identification component includes an identification point, the identification point including one or more of the following: The features identify the corners and / or endpoints of the component shape; Distinguishing it from the color difference points around the feature identification component; The feature identifies the differences in material texture of the component; The feature identification component is used for identification by the robot; The electric door further includes: a second interaction module and a second control module; wherein... The second interaction module is used to receive a first instruction sent by the target robot, the first instruction being used to control the electric door to open, the first instruction being sent by the target robot after determining the position of the electric door using its own recognition sensors; the target robot includes the robot according to any one of claims 1 to 8; The second control module is used to respond to the first command and control the electric door to open.

10. The motorized door of claim 9, wherein, The feature identification component includes more than three identification points, and the identification points are not collinear in a plane parallel to the door component.

11. The motorized door of claim 9, wherein, The feature marking component includes more than three marking points, the marking points are not collinear in a plane parallel to the door component, and at least three of the marking points are located at a height of not less than 30cm.

12. The motorized door of claim 9, wherein, The second interaction module is also used to receive a second instruction sent by the target robot, the second instruction being used to control the electric door to close, the second instruction being sent by the target robot when it detects that it has successfully passed through the electric door; The second control module is also used to respond to the second command and control the electric door to close.

13. The motorized door of claim 9, wherein, The second interaction module is further configured to send first information to the target robot so that the target robot can perform fault detection on the electric door, wherein the first information includes relevant information on the working status of the electric door.

14. The motorized door according to any one of claims 9 to 13, characterized in that, The second interaction module is also used to actively or passively establish a communication connection with one or more robots, establish and store the association between the electric door and the one or more robots, wherein the one or more robots include at least the target robot.

Images