Robot Control Method, Device, Computer Equipment, Readable Storage Medium and Program Product

Abstract

The present application relates to a robot control method, device, computer device, computer-readable storage medium, and computer program product. The method includes: obtaining the current control mode of the robot; a plurality of sensors are integrated on the electronic skin on the outer surface of the robot; determining the current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store the state information of each sensor in the current control mode; determining the trigger state corresponding to each sensor based on the state information of each sensor; and controlling the movement of the robot according to the current control mode when at least one of the sensors is in a triggered state. Using this method can improve efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of robot control, and in particular, to a robot control method, device, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of robot control technology, a key technology called electronic skin has emerged. Covering the outer surface of a robot with electronic skin can endow the robot with a sense of touch similar to that of human skin, enabling the robot to interact with humans more safely and flexibly.

[0003] In traditional technologies, generally, it is necessary to analyze the sensing signals of the sensors on the electronic skin to determine the current situation of the robot, and then adjust the movement of the robot. However, when the number of sensors on the electronic skin is large, analyzing multiple sensing signals simultaneously has the problem of low efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a robot control method, device, computer device, computer-readable storage medium, and computer program product that can improve efficiency for the above technical problems.

[0005] In a first aspect, the present application provides a robot control method, including:

[0006] Obtain the current control mode of the robot; a plurality of sensors are integrated on the electronic skin on the outer surface of the robot;

[0007] Determine the current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store the state information of each sensor in the current control mode;

[0008] Based on the state information of each sensor, determine the trigger state corresponding to each sensor;

[0009] When at least one of the sensors is in a triggered state, control the movement of the robot according to the current control mode.

[0010] In one embodiment, the current control mode includes an anti-collision mode; the determining the trigger state corresponding to each sensor based on the state information of each sensor includes:

[0011] Read the state information corresponding to each sensor from the current register;

[0012] For each sensor, if the state information meets the anti-collision condition, determine that the sensor is in a triggered state;

[0013] If the status information does not meet the anti-collision condition, it is determined that the sensor is in an untriggered state.

[0014] In one embodiment, controlling the movement of the robot according to the current control mode includes:

[0015] Controlling the robot to perform a decelerating movement and recording the continuous deceleration duration of the robot;

[0016] If the continuous deceleration duration does not reach the preset duration, return to the step of reading the status information corresponding to each sensor from the current register, and control the robot to stop decelerating when each sensor is in an untriggered state;

[0017] If the continuous deceleration duration reaches the preset duration, control the robot to stop moving.

[0018] In one embodiment, the current control mode includes an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each sensor; determining the trigger state corresponding to each sensor based on the status information of each sensor includes:

[0019] For each sensor, read the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and read the sensing threshold of the sensor from the threshold register corresponding to the sensor;

[0020] If the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state.

[0021] In one embodiment, controlling the movement of the robot according to the current control mode includes:

[0022] For a target sensor in a triggered state among the sensors, determine the position of the obstacle relative to the robot based on the current pose of the robot and the position of the target sensor on the electronic skin;

[0023] Adjust the movement direction of the robot according to the position of the obstacle relative to the robot.

[0024] In one embodiment, there are multiple obstacles; adjusting the movement direction of the robot according to the position of the obstacle relative to the robot includes:

[0025] Determine the current position of the robot and the desired end position;

[0026] Determine the shortest path from the current position to the end position based on the respective orientations of each of the obstacles relative to the robot;

[0027] Adjust the movement direction of the robot according to the shortest path.

[0028] In a second aspect, the present application further provides a robot control device, including:

[0029] A control mode acquisition module, configured to acquire the current control mode of the robot; a plurality of sensors are integrated on the electronic skin on the outer surface of the robot;

[0030] A register determination module, configured to determine the current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store the state information of each of the sensors in the current control mode;

[0031] A trigger state determination module, configured to determine the respective trigger states corresponding to each of the sensors based on the state information of each of the sensors;

[0032] A motion control module, configured to control the movement of the robot according to the current control mode when at least one of the sensors is in a triggered state.

[0033] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the method described above are implemented.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0035] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0036] The above-mentioned robot control method, device, computer equipment, computer-readable storage medium and computer program product can obtain the current control mode of the robot and determine the control movement situation of the robot at the current moment. Among them, a plurality of sensors are integrated on the electronic skin on the surface of the robot, and each sensor can correspondingly monitor the obstacle situation in a certain direction outside the robot. Then, from the multiple candidate registers deployed by the robot, the current register corresponding to the current control mode for storing the state information of each sensor in the current control mode is determined, and then the trigger state corresponding to each sensor can be determined based on the state information of each sensor. When at least one of the sensors is in the triggered state, it indicates that the robot is close to the obstacle in one or some directions. Therefore, the robot can be controlled to move according to the current control mode. By adopting the above robot control method, the trigger state corresponding to each sensor can be directly determined through the state information stored in the current register corresponding to each current control mode, which can significantly improve the efficiency of robot control. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for describing the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0038] Figure 1 It is an application environment diagram of the robot control method in an embodiment;

[0039] Figure 2 It is a flowchart of the robot control method in an embodiment;

[0040] Figure 3 It is a schematic diagram of the communication connection mode of the robot control method in an embodiment;

[0041] Figure 4 It is a flowchart of the anti-collision mode in the robot control method in an embodiment;

[0042] Figure 5 It is a flowchart of the obstacle avoidance mode in the robot control method in an embodiment;

[0043] Figure 6 It is an electronic skin architecture diagram in the robot control method in an embodiment;

[0044] Figure 7 It is a flowchart of the robot control method in another embodiment;

[0045] Figure 8 It is a structural block diagram of a robot control device in an embodiment;

[0046] Figure 9 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The robot control method provided by the embodiments of the present application can be applied to, for example, Figure 1 the application environment shown. Among them, the server 102 communicates with the robot 104 through a network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or placed in the cloud or other network servers. Among them, the server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Alternatively, the server 102 can also be integrated on the robot 104. The robot 104 refers to a robot used to safely directly interact or cooperate with humans in a common working space. For example, the robot 104 can be a collaborative manipulator, an industrial manipulator or a humanoid robot, etc. Specifically, during the process of the server 102 controlling the robot, obtain the current control mode of the robot 104; a plurality of sensors are integrated on the electronic skin on the surface of the robot 104; determine the current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot 104; the current register is used to store the state information of each sensor in the current control mode; based on the state information of each sensor, determine the triggered state corresponding to each sensor; when at least one of the sensors is in the triggered state, control the movement of the robot 104 according to the current control mode.

[0049] In an exemplary embodiment, as Figure 2 shown, a robot control method is provided. Taking the method applied to the Figure 1 server 102 therein as an example for description, it includes the following steps S202 to step S208. Among them:

[0050] Step S202, obtain the current control mode of the robot.

[0051] Among them, a robot refers to a robot used to safely directly interact or cooperate with humans in a common workspace. For example, the robot can be a collaborative manipulator, an industrial manipulator, a humanoid robot, etc. Multiple sensors are integrated on the electronic skin on the surface of the robot. The electronic skin is a system that can endow a robot or other device with a sense of touch. It mimics the perception function of the human skin. Specifically, the electronic skin is a new type of flexible wearable sensor, which has the characteristics of being thin, light, soft, flexible, etc., and can perceive various external stimuli such as pressure, temperature, humidity, etc. like the human skin, and convert these stimuli into electrical signals for feedback. A sensor is a device that can convert various information in the physical world (such as temperature, light, pressure, gas concentration, etc.) into electrical signals that can be processed by an electronic system. The current control mode refers to the control mode of the robot at the current moment. For example, in this embodiment, the control mode includes two types: a collision avoidance mode and an obstacle avoidance mode. The collision avoidance mode means that when an obstacle is detected within a certain distance, the robot is controlled to decelerate. The obstacle avoidance mode means that when an obstacle is detected in a certain direction within a certain distance, the robot avoids in the opposite direction of that direction.

[0052] Specifically, during the robot control process, the server needs to first obtain the current control mode of the robot to determine the control mode of the robot at the current moment, and then it can control the robot according to this control mode. It can be understood that the operation of obtaining the current control mode of the robot can be an active acquisition or a passive reception.

[0053] Step S204: Determine the current register corresponding to the current control mode from multiple candidate registers deployed by the robot.

[0054] Among them, a candidate register refers to a register in a state of waiting to be selected. The current register is used to store the state information of each sensor in the current control mode.

[0055] Specifically, different control modes correspond to different registers. Therefore, after the server obtains the current control mode of the robot, it also needs to obtain multiple candidate registers deployed by the robot, and determine the current register corresponding to the current control mode from the above-mentioned multiple candidate registers, so as to control the robot according to the information stored in the current register later.

[0056] Step S206: Determine the trigger state corresponding to each sensor based on the state information of each sensor.

[0057] Among them, the trigger state is used to characterize whether the sensor is triggered. That is, the trigger state can include the triggered state and the untriggered state. It can be understood that when the sensor is triggered, it means that there is an obstacle within a certain distance at the relative position of the robot corresponding to the sensor. The state information refers to the information corresponding to the sensor state of the sensor and can be used to reflect the current state of the sensor.

[0058] Specifically, after determining the current register corresponding to the current control mode, the server can obtain the state information of each sensor stored in the current register from the current register, and determine the trigger state corresponding to each sensor according to the above state information. In some specific embodiments, the relationship between the state information and the trigger state can be preset, and the state information can be analyzed according to the above relationship, and then the trigger state corresponding to each sensor can be determined.

[0059] Step S208, when at least one of the sensors is in the triggered state, control the movement of the robot according to the current control mode.

[0060] Specifically, if at least one of the sensors is in the triggered state, it indicates that there is at least one obstacle at a relatively close distance to the robot in each direction of the robot. Therefore, the server can control the movement of the robot according to the current control mode. Exemplarily, since the control modes include the obstacle avoidance mode and the anti-collision mode, the server selects an appropriate coping strategy according to the type of the current control mode to control the movement of the robot.

[0061] For the above robot control method, by obtaining the current control mode of the robot, the control movement situation of the robot at the current moment can be determined. Among them, a plurality of sensors are integrated on the electronic skin on the surface of the robot, and each sensor can correspondingly monitor the obstacle situation in a certain direction outside the robot. Then, from the multiple candidate registers deployed by the robot, the current register corresponding to the current control mode for storing the state information of each sensor in the current control mode is determined, and then based on the state information of each sensor, the trigger state corresponding to each sensor can be determined. When at least one of the sensors is in the triggered state, it indicates that the robot is already relatively close to the obstacle in one or some directions. Therefore, the movement of the robot can be controlled according to the current control mode. By using the above robot control method, the trigger state corresponding to each sensor can be directly determined through the state information stored in the current register corresponding to each current control mode, which can significantly improve the efficiency of robot control.

[0062] In an exemplary embodiment, the current control mode includes an anti-collision mode; based on the respective status information of each sensor, determining the respective trigger status of each sensor, including: reading the respective status information of each sensor from the current register; for each sensor, if the status information meets the anti-collision condition, determining that the sensor is in a triggered state; if the status information does not meet the anti-collision condition, determining that the sensor is in an untriggered state.

[0063] Among them, the anti-collision mode refers to the anti-collision prevention mode, that is, when the robot is in the anti-collision mode, if there is an obstacle within a certain distance, the robot needs to decelerate to prevent the robot from colliding with the obstacle. The anti-collision condition refers to the condition for preventing collision. In this embodiment, the anti-collision condition mainly refers to the status information being 1.

[0064] Specifically, in this embodiment, if the status information is 1, it indicates that the status information meets the anti-collision condition; if the status information is 0, it indicates that the status information does not meet the anti-collision condition. That is, the server can read the respective status information of each sensor from the current register. Then, for each sensor, it is determined whether the status information of the sensor meets the anti-collision condition. If the status information meets the anti-collision condition, it is determined that the sensor is in a triggered state; if the status information does not meet the anti-collision condition, it is determined that the sensor is in an untriggered state.

[0065] In this embodiment, when the current control mode is the anti-collision mode, determining whether the status information of each sensor meets the anti-collision condition can ensure the accuracy of determining the sensor status.

[0066] In an exemplary embodiment, controlling the movement of the robot according to the current control mode includes: controlling the robot to perform a deceleration movement and recording the continuous deceleration duration of the robot; if the continuous deceleration duration does not reach the preset duration, returning to the step of reading the respective status information of each sensor from the current register, and controlling the robot to stop decelerating when all sensors are in an untriggered state; if the continuous deceleration duration reaches the preset duration, controlling the robot to stop moving.

[0067] Among them, the continuous deceleration duration refers to the time length of continuous deceleration. The preset duration refers to the time length set in advance.

[0068] Specifically, in the anti-collision mode and when at least one of the sensors is in a triggered state, the server needs to control the robot to decelerate and record the duration of the robot's continuous deceleration. If the duration of continuous deceleration reaches the preset duration, it indicates that there is still a risk of collision between the obstacle and the robot during the deceleration of the robot. Therefore, it is necessary to control the robot to stop moving. If the duration of continuous deceleration does not reach the preset duration, the step of reading the status information corresponding to each sensor from the current register can be returned to re-judge whether the status information meets the anti-collision condition. If all sensors are in an untriggered state this time, it indicates that the robot and the obstacle are already at a safe distance. Therefore, the robot can be controlled to stop decelerating.

[0069] In this embodiment, by repeatedly reading the status information of the sensors, the distance state between the robot and the obstacle can be continuously determined, and the realization of the anti-collision function between the robot and the obstacle can be accurately ensured.

[0070] In an exemplary embodiment, the current control mode includes an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each sensor; determining the triggered state corresponding to each sensor based on the status information of each sensor includes: for each sensor, reading the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and reading the sensing threshold of the sensor from the threshold register corresponding to the sensor; if the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state.

[0071] Among them, the obstacle avoidance mode refers to the mode of avoiding obstacles. That is, when the robot is in the obstacle avoidance mode, if an obstacle appears on one side of the robot, the robot will move towards the other side to avoid the obstacle. The real-time register is a register that records the real-time sensing value of the sensor. The real-time sensing value is used to characterize the real-time state of the sensor. The sensing threshold stored in the threshold register is a preset value, and it can be understood that the sensing threshold can be set according to the actual situation.

[0072] Specifically, when the current control mode is the obstacle avoidance mode, the register includes two types: a threshold register and a real-time register. The threshold register is used to store the preset sensing threshold, and the real-time register is used to record the real-time sensing value of the sensor. By comparing the real-time sensing value with the sensing threshold, the triggered state of the sensor can be determined according to the comparison result. That is, the server can read the real-time sensing value of the sensor from the real-time register corresponding to each sensor and read the sensing threshold of the sensor from the threshold register corresponding to the sensor. If the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state; if the real-time sensing value is less than the sensing threshold, it is determined that the sensor is in an untriggered state.

[0073] In a specific embodiment, the number of configuration holding registers is 17, with addresses ranging from 0 to 16. Among them, addresses 0 to 7 are four data reference channels for the electronic skin sensors. Each time the power is turned on, the values of the current four channels are read as real-time sensing values. Addresses 8 to 15 correspond to the threshold channels of the four channels, and the register values can be set arbitrarily as sensing thresholds. Only the lower five bits of the 16-bit register at address 16 are valid. The lower five bits correspond to the four sensors, namely CHO, CH1, CH2, and CH3, and the initialization calibration configuration bit of the program from low to high.

[0074] In this embodiment, when the current control mode is the obstacle avoidance mode, there are a threshold register for storing the preset sensing threshold and a real-time register for recording the real-time sensing values of the sensors. By comparing the real-time sensing values with the sensing threshold, the trigger state of the sensors can be determined according to the comparison result, ensuring the accuracy of the determination of the trigger state.

[0075] In an exemplary embodiment, controlling the movement of the robot according to the current control mode includes: for each target sensor in the triggered state among the sensors, determining the relative position of the obstacle with respect to the robot based on the current pose of the robot and the position of the target sensor on the electronic skin; adjusting the movement direction of the robot according to the relative position of the obstacle with respect to the robot.

[0076] Among them, the current pose refers to the position and orientation of the robot in three-dimensional space at the current moment.

[0077] Specifically, for each target sensor in the triggered state among the sensors, the server can first determine the position of the target sensor on the electronic skin, and combine the current pose of the robot to determine the relative position of the obstacle with respect to the robot. After determining the relative position of the obstacle with respect to the robot, the server can adjust the movement direction of the robot according to this position. In a specific embodiment, the position of the target sensor on the electronic skin is on the left side of the electronic skin, and the current pose of the robot is represented as the robot running normally on the horizontal ground. Then the relative position of the obstacle with respect to the robot is on the left side. Therefore, the movement direction of the robot can be adjusted to deviate to the right side.

[0078] In this embodiment, adjusting the movement direction of the robot according to the current pose of the robot and the position of the target sensor on the electronic skin can ensure the accuracy of the adjustment of the robot's movement direction, thereby improving the efficiency of robot control.

[0079] In an exemplary embodiment, there are multiple obstacles; adjusting the moving direction of the robot according to the relative orientation of the obstacles with respect to the robot includes: determining the current position of the robot and the end position it expects to reach; determining the shortest path from the current position to the end position based on the relative orientation of each obstacle with respect to the robot; and adjusting the moving direction of the robot according to the shortest path.

[0080] Specifically, in the case where there are multiple obstacles, in order to improve the efficiency of robot control, the shortest path that the robot can travel while avoiding obstacles can be planned for the robot. That is, the server can first determine the current position of the robot and the end position it expects to reach, and then determine the shortest path from the current position to the end position based on the relative orientation of each obstacle with respect to the robot. This shortest path refers to the shortest path for the robot to reach the end position from the current position while avoiding all obstacles. Therefore, the server can adjust the moving direction of the robot according to the shortest path, thereby improving the efficiency of robot control.

[0081] In a specific embodiment, a robot control method in an actual application scenario is also provided, and the main functions implemented are non-contact safety collision stop and active obstacle avoidance (the two functions need to be manually configured and switched).

[0082] (1) The non-contact safety collision stop is mainly that when a conductor approaches the body within a certain distance, the motion controller controls the robot body to decelerate and stop according to the signal feedback from the electronic skin sensor board.

[0083] (2) The active obstacle avoidance mode is mainly that when it detects that there is a conductor approaching around, it will perform dynamic trajectory planning to always keep the collision detection signal of the sensor board within the safe threshold range.

[0084] The purpose of this embodiment is to solve the disadvantages of weak anti-interference ability, slow response time, weak scalability, high cost, low sensitivity, contact type, etc. of the electronic skin currently on the market, and to achieve an efficient and safe non-contact electronic skin for the collaborative manipulator.

[0085] In this embodiment, the overall system consists of four parts: an electric control box, a collaborative robot body, an electronic skin sensor board, and a sensor.

[0086] Connection method: As Figure 3As shown in the figure, the electrical skin sensor board (electronic skin) is connected to the four sensors through low-impedance conductive cables. The electronic skin sensor board communicates with each joint control board of the collaborative robot body through RS485. Each electronic skin sensor board acts as a MODBUS slave for each joint control board. Each joint control board communicates with the motion controller body through ETHERCAT, thus realizing the non-contact safety collision stop function.

[0087] Control method: For the joint control board, the electronic skin sensor board acts as a MODBUS slave. The joint control board communicates with the electronic skin sensor board through RS485. In the XML protocol, there is a configuration SDO index to read the data in the MODUBUS slave register. The controller needs to read and configure the values in the registers of the electronic skin sensor board through the bus. The registers in the sensor board are divided into input registers and holding registers. The register configuration is as follows:

[0088] Input registers: The number of configured registers is 9, and the addresses range from 0 to 8. Among them, addresses 0 to 7 are the input channels of the four electronic skin sensors. Each sensor channel occupies two register addresses. Taking CH0 as an example, addresses 0 to 1 correspond to the sensor data input channel of CH0. Address 0 is the low 16-bit data input channel of CH0, and address 1 is the high 12-bit data input channel of CH0. Only the low four bits of the 16-bit register corresponding to address 8 are valid. The low four bits correspond to the trigger states of the four sensor channels CH0, CH1, CH2, and CH3 from low to high. As Figure 4 shown, it is possible to determine whether a sensor is triggered by judging whether any BIT state in the low four bits of the input register at address 8 is 1, and then perform a series of subsequent operations.

[0089] Holding registers: The number of configured registers is 17, and the addresses range from 0 to 16. Among them, addresses 0 to 7 are the data reference channels of the four electronic skin sensors. After each power-on, the current values of the four channels will be read from the input registers as reference values. Addresses 8 to 15 correspond to the threshold channels of the four channels, and the register values can be set arbitrarily as the trigger threshold (sensing threshold) of the electronic skin. Only the low five bits of the 16-bit register at address 16 are valid. The low five bits correspond to CH0, CH1, CH2, CH3, and the initialization calibration configuration bit of the program. As Figure 5 shown, it is possible to determine whether it is necessary to adjust the motion path of the robot by judging whether the value of any channel in the four-channel input register of the electronic skin exceeds the set sensing threshold.

[0090] As Figure 6As shown in the figure, the control architecture of this embodiment mainly centers around the electronic skin PCB board, collecting and converting the data of capacitive sensors in real time upwards, and transmitting the data of the input register and the holding register in real time downwards. It includes a power conversion part of converting 5V to 3.3V. The MCU is controlled by STM32, and the chip for collecting the data of the capacitive sensor board uses FDC2214 of TI, which supports simultaneous acquisition and conversion of up to 4-channel data at most. The control architecture is shown in the following figure:

[0091] The ways for the safe electronic skin to achieve non-contact human-robot collaboration mainly include the following steps and technical features:

[0092] (1) Early perception and stop before collision:

[0093] The safe skin can perceive the presence of an object (such as a person or an obstacle) approaching the robot in advance. This perception usually occurs within a certain range from the robot (such as 10 - 20 cm), and can make a quick response within an extremely short time (such as 10 ms), pausing the operation of the robot to avoid collisions. This pre-collision perception technology does not require reducing the speed of the robot in advance, and can ensure the safety of human-robot collaboration while maintaining production efficiency.

[0094] (2) Omnidirectional perception:

[0095] The safe skin is worn and wrapped around the outside of the robot, providing 360-degree omnidirectional perception ability. This means that no matter from which direction an object approaches the robot, it can be detected in time, thus avoiding detection blind spots.

[0096] (3) High sensitivity and fast response:

[0097] The safe skin is characterized by high sensitivity and can respond to the approach of an object within an extremely short time. This fast response ability ensures that the robot can quickly stop when detecting an obstacle, thus avoiding collisions.

[0098] (4) Automatic obstacle avoidance function:

[0099] Combined with advanced AI algorithm technology, the safe skin also has the function of automatic obstacle avoidance. When detecting an obstacle, the robot will automatically select the optimal path to execute the task and avoid colliding with the obstacle.

[0100] (5) Compatibility and ease of use:

[0101] The safe skin can be installed not only on the robotic arm but also in the end effector, effectively protecting all mechanical structures from contact collisions. In addition, the safe skin adopts a plug-and-play design, which reduces the usage threshold, and the advantages in later maintenance and cost are also very obvious.

[0102] (6) Intelligent interaction and self-learning ability:

[0103] Some advanced collaborative robots also have intelligent interaction panels and self-learning abilities. They can understand human intentions through AI deep learning algorithms and perform tasks by imitating human actions. This human-centered interaction method further improves the robot's perception and response capabilities and usability.

[0104] In summary, through characteristics such as early perception, all-round perception, high sensitivity and fast response, automatic obstacle avoidance function, and intelligent interaction and self-learning ability, the safe electronic skin realizes non-contact human-machine collaboration, providing the possibility for the large-scale application of collaborative robots and their entry into a wider range of scenarios.

[0105] In a specific embodiment, as Figure 7 shown, a robot control method is also provided, including:

[0106] Step S701: Obtain the current control mode of the robot, and determine the current register corresponding to the current control mode from multiple candidate registers deployed by the robot;

[0107] Among them, multiple sensors are integrated on the electronic skin on the surface of the robot; the current register is used to store the status information of each sensor in the current control mode; the current control mode includes an anti-collision mode and an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each sensor;

[0108] Step S702: Read the status information corresponding to each sensor from the current register;

[0109] Step S703: For each sensor, if the status information meets the anti-collision condition, determine that the sensor is in a triggered state;

[0110] Step S704: If the status information does not meet the anti-collision condition, determine that the sensor is in an untriggered state;

[0111] Step S705: When at least one of the sensors is in a triggered state, control the robot to decelerate and record the continuous deceleration duration of the robot;

[0112] Step S706: If the continuous deceleration duration does not reach the preset duration, return to the step of reading the status information corresponding to each sensor from the current register, and when all sensors are in an untriggered state, control the robot to stop decelerating;

[0113] Step S707: If the continuous deceleration duration reaches the preset duration, control the robot to stop moving;

[0114] Step S708: For each sensor, read the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and read the sensing threshold of the sensor from the threshold register corresponding to the sensor.

[0115] Step S709: If the real-time sensing value is greater than or equal to the sensing threshold, determine that the sensor is in a triggered state.

[0116] Step S710: When at least one of the sensors is in a triggered state, for the target sensors in the triggered state among the sensors, determine the relative orientation of the obstacle with respect to the robot based on the current pose of the robot and the position of the target sensor on the electronic skin.

[0117] Wherein, there are multiple obstacles.

[0118] Step S711: Determine the current position of the robot and the desired end position.

[0119] Step S712: Based on the relative orientations of the obstacles with respect to the robot respectively, determine the shortest path from the current position to the end position, and adjust the movement direction of the robot according to the shortest path.

[0120] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0121] Based on the same inventive concept, an embodiment of the present application further provides a robot control device for implementing the above-mentioned robot control method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following robot control devices can refer to the limitations on the robot control method in the above text, and will not be repeated here.

[0122] In an exemplary embodiment, as Figure 8As shown, a robot control device 800 is provided, including: a control mode acquisition module 802, a register determination module 804, a trigger state determination module 806, and a motion control module 808, where:

[0123] The control mode acquisition module 802 is configured to acquire the current control mode of the robot; a plurality of sensors are integrated on the electronic skin on the outer surface of the robot;

[0124] The register determination module 804 is configured to determine the current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store the state information of each sensor in the current control mode;

[0125] The trigger state determination module 806 is configured to determine the trigger state corresponding to each sensor based on the state information of each sensor;

[0126] The motion control module 808 is configured to control the motion of the robot according to the current control mode when at least one of the sensors is in the triggered state.

[0127] In an exemplary embodiment, the current control mode includes a collision avoidance mode. In this embodiment, the trigger state determination module 806 is configured to:

[0128] Read the state information corresponding to each sensor from the current register;

[0129] For each sensor, if the state information meets the collision avoidance condition, it is determined that the sensor is in the triggered state;

[0130] If the state information does not meet the collision avoidance condition, it is determined that the sensor is in the untriggered state.

[0131] In an exemplary embodiment, the motion control module 808 is configured to:

[0132] Control the robot to perform a deceleration motion and record the continuous deceleration duration of the robot;

[0133] If the continuous deceleration duration does not reach the preset duration, return to the step of reading the state information corresponding to each sensor from the current register, and control the robot to stop decelerating when all sensors are in the untriggered state;

[0134] If the continuous deceleration duration reaches the preset duration, control the robot to stop moving.

[0135] In an exemplary embodiment, the current control mode includes an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each sensor. In this embodiment, the trigger state determination module 806 is further configured to:

[0136] For each sensor, read the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and read the sensing threshold of the sensor from the threshold register corresponding to the sensor;

[0137] If the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state.

[0138] In an exemplary embodiment, the motion control module 808 includes:

[0139] An orientation determination unit, configured to, for a target sensor in a triggered state among the sensors, determine the orientation of the obstacle relative to the robot based on the current pose of the robot and the position of the target sensor on the electronic skin;

[0140] A motion direction adjustment unit, configured to adjust the motion direction of the robot according to the orientation of the obstacle relative to the robot.

[0141] In an exemplary embodiment, there are multiple obstacles. In this embodiment, the motion direction adjustment unit is specifically configured to:

[0142] Determine the current position of the robot and the desired end position;

[0143] Based on the respective orientations of the obstacles relative to the robot, determine the shortest path from the current position to the end position;

[0144] Adjust the motion direction of the robot according to the shortest path.

[0145] Each module in the above robot control device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0146] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 9As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a robot control method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0147] Those skilled in the art can understand that Figure 9 the structure shown in

[0148] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0149] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of the above method are implemented.

[0150] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the above method are implemented.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0153] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0154] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A robot control method, characterized in that: The method comprises: Acquire the current control mode of the robot; the electronic skin on the robot's exterior is integrated with a plurality of sensors; Determine a current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store state information of each of the sensors under the current control mode; Based on the state information of each of the sensors, determining the trigger state corresponding to each of the sensors; When at least one of the sensors is in a triggered state, controlling the movement of the robot according to the current control mode; The current control mode includes an anti-collision mode; and determining the trigger state corresponding to each of the sensors based on the state information of each of the sensors includes: Reading the status information corresponding to each of the sensors from the current register; For each of the sensors, if the state information satisfies the anti-collision condition, determining that the sensor is in a triggered state; If the state information does not satisfy the anti-collision condition, determining that the sensor is in an untriggered state; The controlling the robot movement according to the current control mode comprises: Controlling the robot to perform deceleration movement, and recording the continuous deceleration duration of the robot; If the continuous deceleration time does not reach the preset time, returning to the step of reading the state information corresponding to each of the sensors from the current register, and controlling the robot to stop decelerating when each of the sensors is in an untriggered state; If the continuous deceleration time reaches the preset time, the robot is controlled to stop moving.

2. The method according to claim 1, characterized in that The current control mode includes an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each of the sensors; and determining the trigger state corresponding to each of the sensors based on the state information of each of the sensors includes: For each of the sensors, read the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and read the sensing threshold of the sensor from the threshold register corresponding to the sensor; If the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state.

3. The method according to claim 2, characterized in that The controlling the robot movement according to the current control mode comprises: For a target sensor in a triggered state among the sensors, based on the current posture of the robot and the position of the target sensor on the electronic skin, determine the position of the obstacle relative to the robot; The movement direction of the robot is adjusted according to the position of the obstacle relative to the robot.

4. The method according to claim 3, characterized in that There are multiple obstacles; and adjusting the movement direction of the robot according to the positions of the obstacles relative to the robot includes: Determine the current position of the robot and the desired destination position; Determining the shortest path from the current position to the end position based on the respective positions of the obstacles relative to the robot; According to the shortest path, the movement direction of the robot is adjusted.

5. A robot control device, characterized in that: The device comprises: A control mode acquisition module is used to acquire the current control mode of the robot; the electronic skin on the robot's exterior is integrated with multiple sensors; A register determination module, used to determine a current register corresponding to the current control mode from a plurality of candidate registers deployed by the robot; the current register is used to store state information of each of the sensors under the current control mode; the current control mode includes an anti-collision mode; A trigger state determination module, used for determining the trigger state corresponding to each of the sensors based on the state information of each of the sensors; A motion control module, configured to control the motion of the robot according to the current control mode when at least one of the sensors is in a triggered state; The trigger state determination module is further used to: read the state information corresponding to each of the sensors from the current register; For each of the sensors, if the state information satisfies the anti-collision condition, determining that the sensor is in a triggered state; If the state information does not satisfy the anti-collision condition, determining that the sensor is in an untriggered state; The motion control module is also used to: control the robot to perform deceleration motion and record the continuous deceleration time of the robot; If the continuous deceleration time does not reach the preset time, returning to the step of reading the state information corresponding to each of the sensors from the current register, and controlling the robot to stop decelerating when each of the sensors is in an untriggered state; If the continuous deceleration time reaches the preset time, the robot is controlled to stop moving.

6. The device according to claim 5, characterized in that The current control mode includes an obstacle avoidance mode; the current register includes a threshold register and a real-time register corresponding to each of the sensors; the trigger state determination module is further used for: For each of the sensors, read the real-time sensing value of the sensor from the real-time register corresponding to the sensor, and read the sensing threshold of the sensor from the threshold register corresponding to the sensor; If the real-time sensing value is greater than or equal to the sensing threshold, it is determined that the sensor is in a triggered state.

7. The device according to claim 6, characterized in that The motion control module comprises: A position determination unit, for determining the position of an obstacle relative to the robot based on the current posture of the robot and the position of the target sensor on the electronic skin for a target sensor in a triggered state among the sensors; The movement direction adjustment unit is used to adjust the movement direction of the robot according to the position of the obstacle relative to the robot.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images