Robotic arm collision detection system, method, robotic arm, robot, and chip

Abstract

The application belongs to the technical field of mechanical arms, and provides a mechanical arm collision detection system, a method, a mechanical arm, a robot and a chip, wherein the mechanical arm collision detection system comprises a tactile sensor arranged on a mechanical arm; and a controller connected with the tactile sensor; the controller is configured with a collision detection function, and the collision detection function comprises: determining a collision state of the mechanical arm based on a sensing signal of the tactile sensor, and the sensing signal is used to represent force information in at least one direction. The technical scheme provided in the application can effectively improve the collision detection precision and reduce the probability of collision damage.

Description

Technical Field

[0001] This application belongs to the field of robotic arm technology, and particularly relates to a robotic arm collision detection system, method, robotic arm, robot and chip. Background Technology

[0002] Collision detection is an important technical means for robot safety control. Currently, common collision detection methods for robot arms mainly include contact collision detection methods based on current loops.

[0003] However, contact collision detection methods based on current loops have low detection accuracy and are prone to causing impact injuries because they detect changes in joint current caused by collision torque. Summary of the Invention

[0004] This application provides a robotic arm collision detection system, method, robotic arm, robot, and chip, which can improve collision detection accuracy and reduce the probability of collision damage.

[0005] In a first aspect, this application provides a robotic arm collision detection system, comprising:

[0006] Tactile sensors installed on the robotic arm;

[0007] And a controller connected to the tactile sensor;

[0008] The controller is equipped with a collision detection function, which includes: determining the collision state of the robotic arm based on the sensing signal of the tactile sensor, wherein the sensing signal is used to characterize the force information in at least one direction.

[0009] Based on the first aspect of this application, in a first possible implementation, the tactile sensor includes a plurality of tactile sensing units, each of which generates a corresponding sensing signal when a corresponding area is touched;

[0010] The method of determining the collision state of the robotic arm based on the sensing signals of the tactile sensor is as follows: the collision state of the robotic arm is determined based on the sensing signals of two or more tactile sensing units in the collision area when it is touched.

[0011] Based on the first possible implementation of the first aspect of this application, in a second possible implementation, determining the collision state of the robotic arm based on the sensing signals of two or more tactile sensing units within the collision area when touched includes:

[0012] The collision state of the robotic arm is determined based on a first average value of the sensing signals from the two or more tactile sensing units; or,

[0013] The collision state of the robotic arm is determined based on the maximum value of the sensing signals from the two or more tactile sensing units and the second average value of the sensing signals from the adjacent tactile sensing units of the tactile sensing unit corresponding to the maximum value.

[0014] Based on the second possible implementation of the first aspect of this application, in the third possible implementation, the controller is configured with a first collision detection condition and a second collision detection condition;

[0015] Determining the collision state of the robotic arm based on the sensing signals from the two or more tactile sensing units includes:

[0016] When the first average value is greater than or equal to the first threshold, the first collision detection condition is met, and the robotic arm is determined to be in the collision state; or...

[0017] When the maximum value is greater than or equal to the second threshold and the second average value is greater than or equal to the third threshold, the second collision detection condition is met, and the robotic arm is determined to be in the collision state; wherein, the second threshold is greater than the third threshold.

[0018] Based on the third possible implementation of the first aspect of this application, in the fourth possible implementation, the collision state includes a first collision state or a second collision state;

[0019] Determining the collision state of the robotic arm based on the sensing signals from the two or more tactile sensing units includes:

[0020] When the first average value is greater than or equal to the first threshold and less than or equal to the fourth threshold, or when the second average value is greater than or equal to the third threshold and less than or equal to the fourth threshold, the collision state of the robotic arm is determined to be the first collision state.

[0021] When the first average value is greater than the fourth threshold, or when the second average value is greater than the fourth threshold, the collision state of the robotic arm is determined to be the second collision state;

[0022] Wherein, the fourth threshold is greater than the first threshold, and the fourth threshold is greater than the third threshold.

[0023] Based on the first possible implementation of the first aspect of this application, in the fifth possible implementation, the tactile sensor is disposed on the outer surface of the robotic arm, and the tactile sensing units are arranged in an array on the outer surface of the robotic arm.

[0024] Based on any possible implementation of the first aspect of this application, in the sixth possible implementation, the controller is configured with a collision avoidance function, the collision avoidance function including: if the robotic arm is in motion, driving the robotic arm to move according to a preset control mode based on the sensing signal and the collision state.

[0025] Based on the sixth possible implementation of the first aspect of this application, in the seventh possible implementation, the collision state includes a first collision state or a second collision state, and the preset control mode includes at least one of the following: a rollback control mode and an admittance control mode;

[0026] The method of driving the robotic arm to move according to a preset control mode based on the sensing signal and the collision state includes:

[0027] When the collision state is the first collision state, the robotic arm is driven to move according to the admittance control mode based on the sensing signal.

[0028] When the collision state is the second collision state, the robotic arm is driven to move according to the retraction control mode based on the sensing signal.

[0029] Based on the seventh possible implementation of the first aspect of this application, in the eighth possible implementation, the step of driving the robotic arm to move according to the admittance control mode based on the sensing signal includes:

[0030] Based on the sensing signal, the operating speed is determined, and the robotic arm is driven to move continuously at the operating speed in the admittance control mode until the robotic arm is no longer in the first collision state.

[0031] The step of driving the robotic arm to move according to the retraction control mode based on the sensing signal includes:

[0032] Based on the sensing signal, the displacement direction is determined, and after the robotic arm is controlled to stop, the robotic arm is driven to move a preset step length along the displacement direction.

[0033] Based on any possible implementation of the first aspect of this application, in the ninth possible implementation, the controller is configured with a touch teaching function, the touch teaching function including: if the robotic arm is in a stationary state, driving the robotic arm to move based on the sensing signal in a preset teaching mode.

[0034] Secondly, embodiments of this application provide a collision detection method for a robotic arm, including:

[0035] The collision state of the robotic arm is determined based on the sensing signals of the tactile sensors, which are used to characterize the force information in at least one direction. The tactile sensors are disposed on the robotic arm.

[0036] Based on the second aspect of this application, in a first possible implementation, the tactile sensor includes a plurality of tactile sensing units, each of which generates a corresponding sensing signal when a corresponding area is touched;

[0037] Determining the collision state of the robotic arm based on the sensing signal from the tactile sensor includes:

[0038] The collision state of the robotic arm is determined based on the sensing signals from two or more tactile sensing units within the collision area when it is touched.

[0039] Based on the first possible implementation of the second aspect of this application, in the second possible implementation,

[0040] Determining the collision state of the robotic arm based on the sensing signals from the two or more tactile sensing units includes:

[0041] The collision state of the robotic arm is determined based on a first average value of the sensing signals from the two or more tactile sensing units; or,

[0042] The collision state of the robotic arm is determined based on the maximum value of the sensing signals from the two or more tactile sensing units and the second average value of the sensing signals from the adjacent tactile sensing units of the tactile sensing unit corresponding to the maximum value.

[0043] Based on the second possible implementation of the second aspect of this application, in the third possible implementation...

[0044] Determining the collision state of the robotic arm based on the sensing signals from the two or more tactile sensing units includes:

[0045] When the first average value is greater than or equal to the first threshold, the first collision detection condition is met, and the robotic arm is determined to be in the collision state; or...

[0046] When the maximum value is greater than or equal to the second threshold and the second average value is greater than or equal to the third threshold, the second collision detection condition is met, and the robotic arm is determined to be in the collision state; wherein, the second threshold is greater than the third threshold.

[0047] Based on the third possible implementation of the second aspect of this application, in the fourth possible implementation,

[0048] The collision state includes a first collision state or a second collision state;

[0049] Determining the collision state of the robotic arm based on the sensing signals from the two or more tactile sensing units includes:

[0050] When the first average value is greater than or equal to the first threshold and less than or equal to the fourth threshold, or when the second average value is greater than or equal to the third threshold and less than or equal to the fourth threshold, the collision state of the robotic arm is determined to be the first collision state.

[0051] When the first average value is greater than the fourth threshold, or when the second average value is greater than the fourth threshold, the collision state of the robotic arm is determined to be the second collision state;

[0052] Wherein, the fourth threshold is greater than the first threshold, and the fourth threshold is greater than the third threshold.

[0053] In a fifth possible implementation, based on any possible implementation of the second aspect of this application, after determining the collision state of the robotic arm based on the sensing signal from the tactile sensor, the method further includes:

[0054] If the robotic arm is in motion, it is driven to move according to a preset control mode based on the sensing signal and the collision state.

[0055] Based on the fifth possible implementation of the second aspect of this application, in the sixth possible implementation, the collision state includes a first collision state or a second collision state, and the preset control mode includes at least one of the following: a rollback control mode and an admittance control mode;

[0056] The method of driving the robotic arm to move according to a preset control mode based on the sensing signal and the collision state includes:

[0057] When the collision state is the first collision state, the robotic arm is driven to move according to the admittance control mode based on the sensing signal.

[0058] When the collision state is the second collision state, the robotic arm is driven to move according to the retraction control mode based on the sensing signal.

[0059] Based on the sixth possible implementation of the second aspect of this application, in the seventh possible implementation, the step of driving the robotic arm to move according to the admittance control mode based on the sensing signal includes:

[0060] Based on the sensing signal, the operating speed is determined, and the robotic arm is driven to move continuously at the operating speed in the admittance control mode until the robotic arm is no longer in the first collision state.

[0061] The step of driving the robotic arm to move according to the retraction control mode based on the sensing signal includes:

[0062] Based on the sensing signal, the displacement direction is determined, and after the robotic arm is controlled to stop, the robotic arm is driven to move a preset step length along the displacement direction.

[0063] In an eighth possible implementation, based on any possible implementation of the second aspect of this application, after determining the collision state of the robotic arm based on the sensing signal from the tactile sensor, the method further includes:

[0064] If the robotic arm is stationary, it is driven to move in a preset teaching mode based on the sensing signal.

[0065] Thirdly, this application provides a robotic arm, including a tactile sensor, a memory, and a processor disposed on the robotic arm, wherein the processor is used to read and execute a computer program stored in the memory to implement the steps of the method described in the second aspect.

[0066] Fourthly, embodiments of this application provide a robot, including the robotic arm described in the third aspect.

[0067] Fifthly, embodiments of this application provide a chip including a processor, the processor being configured to read and execute a computer program stored in a memory to implement the steps of the method described in the second aspect.

[0068] As can be seen from the above, this application places a tactile sensor on the robotic arm and determines the collision state of the robotic arm based on the sensing signal of the tactile sensor. Since the contact-type collision detection of the current loop detects the change in joint current caused by the collision torque, the detection accuracy is low and it is prone to misjudgment. This application detects the collision state based on the sensing signal of the tactile sensor. When the robotic arm collides, it can detect the force information in at least one direction, thereby improving the collision detection accuracy and facilitating the timely determination of the collision state. This reduces the probability of impact injury caused by the collision, making the robotic arm more convenient and less costly in practical applications. It has strong ease of use and practicality. Attached Figure Description

[0069] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1This is a schematic diagram of the collision detection system structure provided in an embodiment of this application;

[0071] Figure 2 This is a schematic diagram of a tactile sensor setting method provided in an embodiment of this application;

[0072] Figure 3 This is a schematic diagram of another tactile sensor setting method provided in the embodiments of this application;

[0073] Figure 4 This is a schematic diagram of the layout of the tactile sensing unit in the tactile sensing area provided in the embodiments of this application;

[0074] Figure 5 These are schematic diagrams illustrating different collision states provided in embodiments of this application;

[0075] Figure 6 This is a schematic diagram of a robotic arm collision detection application scenario provided in an embodiment of this application;

[0076] Figure 7 This is a flowchart illustrating the robotic arm collision detection method provided in the embodiments of this application. Detailed Implementation

[0077] To make the objectives, methods, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0078] In this document, "and / or" is merely a way of describing the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Furthermore, in the description of the embodiments in this application, unless otherwise stated, "multiple" refers to two or more (i.e., more than two), and "at least one" or "one or more" refers to one, two, or more than two.

[0079] References to “one embodiment” or “some embodiments” as described in this specification mean that one or more embodiments of this application include a particular feature, structure, or characteristic described in connection with that embodiment. The terms “comprising,” “including,” “having,” and variations thereof mean “including, but not limited to,” unless otherwise specifically emphasized.

[0080] Currently, the main collision detection methods for robotic arms include contact collision detection based on current loops. However, this detection method detects changes in joint current caused by collision torque, which requires a large external force for the current loop to be detected. Furthermore, it is impossible to determine the exact magnitude of this "large external force," resulting in low collision detection accuracy and problems such as contact damage to the robotic arm or high-speed misjudgment failure.

[0081] Based on the above problems, this application provides a detailed description of a robotic arm collision detection system and its specific embodiments.

[0082] Figure 1 A robotic arm collision detection system is illustrated in one embodiment, including a tactile sensor 101 mounted on the robotic arm and a controller 102 connected to the tactile sensor 101. The controller 102 is equipped with a collision detection function, which includes determining the collision state of the robotic arm based on the sensing signal from the tactile sensor 101. This sensing signal can characterize force information in at least one direction. The collision state can be the state of the robotic arm when it encounters an obstacle during operation. Determining the collision state through the sensing signal facilitates subsequent control of the robotic arm's movement, preventing impact injuries. In this application, the tactile sensor is mounted on the robotic arm, and the collision state is detected based on the sensing signal during the robotic arm's movement. This method is applicable to detecting collisions with various obstacles, including metals and non-metals, greatly expanding its application range. Since the sensing signal can characterize force information in at least one direction, it facilitates timely determination of the collision state, improving the accuracy of collision detection, reducing the probability of false collision detection, and decreasing the probability of impact injuries caused by collisions. This makes the robotic arm more convenient and cost-effective in practical applications.

[0083] In some embodiments, the controller may be located inside the robotic arm, or it may be located outside the robotic arm and may be directly or indirectly connected to the tactile sensor.

[0084] In some embodiments, such as Figure 2As shown, a tactile sensor can be attached to the surface of the robotic arm's end effector. When an object (such as an obstacle) comes into contact with the end effector, it generates a corresponding sensing signal. This signal triggers the controller to drive the robotic arm to perform corresponding movements. For example, the magnitude of the sensing signal can determine the collision state of the robotic arm, thereby causing it to stop or reduce its speed. It should be understood that, on the one hand, attaching the tactile sensor to the surface of the robotic arm's end effector does not limit it to being exposed. In practical applications, after attaching the tactile sensor to the end effector, a protective layer or shell can be further added to protect it. The protective layer or shell should be designed to not affect the sensing accuracy of the tactile sensor. On the other hand, as... Figure 2 and Figure 3 As shown, the tactile sensor can be completely or partially covered on the outer surface of the robotic arm, and the specific configuration can be determined according to the structural shape of the robot to which the robotic arm belongs.

[0085] For example, the sensor can be set at other locations on the robotic arm, and the principle of triggering and control methods for different locations is the same as that in the embodiments of this application.

[0086] In some embodiments, the robotic arm can determine the collision state based on different sensing signals and drive the robotic arm to perform corresponding movements based on different collision states. For multi-axis robotic arms (such as six-axis robotic arms), in practical applications, the end effector of the robotic arm may need to perform multi-degree-of-freedom movements (such as completing linear movements along the X, Y, or Z axes). Therefore, the tactile sensor in this embodiment can be a tactile sensor capable of detecting three-dimensional forces (such as piezoresistive tactile sensors, piezoelectric tactile sensors, etc.). These types of tactile sensors can detect tactile forces in the X, Y, and Z axes and generate more informative sensing signals. Based on this, corresponding collision conditions and motion parameters are configured for various sensing signals, so that the controller can drive the robotic arm to perform corresponding motion modes based on the collision state of the robotic arm, thereby realizing the timely and accurate obstacle avoidance function of the robotic arm and reducing the probability of the robotic arm being injured by collision.

[0087] In some embodiments, a tactile sensor is disposed on the outer surface of the robotic arm, forming a tactile sensing area. For example... Figure 2 As shown, a ring-shaped tactile sensor 101 can be installed at the end of the robotic arm (the area inside the circle in the figure is a close-up view of the end of the robotic arm); as Figure 3 A schematic diagram of two tactile sensors 101 installed at the end of a robotic arm is shown (the area inside the circle in the diagram is a close-up view of the end of the robotic arm).

[0088] In some embodiments, the robotic arm collision detection system includes a tactile sensor disposed at the end of the robotic arm. The tactile sensor may include multiple tactile sensing units, each of which generates a corresponding sensing signal when touched at a corresponding location. Based on the sensing signals generated in real time by the tactile sensor, one or more of the following information can be identified: the location of the triggered sensing area of ​​the triggered tactile sensing unit, and the number of tactile sensing units triggered in real time. Exemplarily, the distinction of tactile sensing areas can be achieved through hardware and / or software configuration. For hardware methods, this can be achieved by setting two or more tactile sensors at the end of the robotic arm; in specific applications, two or more tactile sensors can be distributed on different planes to form two or more distinguished tactile sensing areas, such as... Figure 3 A schematic diagram is provided showing two tactile sensors 101 installed at the end effector of a robotic arm. Of course, four tactile sensors can also be installed at the end effector; the specific number of tactile sensors can be set according to the structural characteristics of the robotic arm. For software configuration, the tactile sensing area of ​​the same tactile sensor can be divided into two or more relatively independent tactile sensing areas, thus forming two or more distinct tactile sensing areas; for example... Figure 2 As shown, a ring-shaped tactile sensor 101 can be installed at the end of the robotic arm, and the tactile sensing area of ​​the tactile sensor can be divided into two or more tactile sensing areas. This embodiment does not limit the number of tactile sensors.

[0089] In some embodiments, the tactile sensor forms a tactile sensing area including multiple tactile sensing units, each of which generates a corresponding sensing signal when its corresponding tactile sensing area is touched; the collision state of the robotic arm is determined based on the sensing signals of two or more tactile sensing units within the collision area when touched. Figure 4 As shown, the tactile sensing units are arranged in an array in the tactile sensing area, such as the multi-row arrangement of tactile sensing units 1 to 16.

[0090] It should be noted that, Figure 4 This is merely an example and does not specifically limit the arrangement of the tactile sensing unit on the outer surface of the robotic arm. Other layouts based on the structural features of the outer surface of the robotic arm are also possible.

[0091] In some embodiments, the tactile sensor can detect at least one-dimensional tactile pressure; the sensing signal generated by each tactile sensing unit when touched can characterize the tactile pressure corresponding to the direction of the coordinate axis. Alternatively, the resultant force of the one-dimensional tactile pressure or multi-dimensional tactile pressure corresponding to each tactile sensing unit can be obtained from the sensing signal; such as... Figure 5The tactile pressure in the three directions of x1, y1 and z1, or the tactile force in the three directions of x2, y2 and z2, or the resultant force of the tactile pressure in the three directions respectively.

[0092] In some embodiments, determining the collision state of a robotic arm based on sensing signals from two or more tactile sensing units includes: determining the collision state of the robotic arm based on a first average value of sensing signals from two or more tactile sensing units within the collision area when the arm is touched; or, determining the collision state of the robotic arm based on the maximum value of sensing signals from two or more tactile sensing units and a second average value of sensing signals from tactile sensing units adjacent to the maximum value.

[0093] For example, a collision region S can be determined based on the location of the tactile sensing units that generate sensing signals in real time. This collision region S includes the locations of N tactile sensing units (N not less than 2) that generate sensing signals in real time. Using F(f i f can represent the tactile pressure vector of the sensed signal detected in the collision region S; i This represents the resultant force of one-dimensional or multi-dimensional tactile pressure corresponding to the sensing signal generated by the i-th tactile sensing unit in the collision area S. i represents the number of the tactile sensing unit in the collision area S. Each numbered tactile sensing unit can uniquely correspond to a certain position on the outer surface of the robotic arm. i can take the value of an integer from 1 to N.

[0094] On the one hand, the aforementioned collision area S is the area formed by the location of all the tactile sensing units that are triggered to generate sensing signals; on the other hand, based on the specific structure that the obstacle may have, the tactile sensing units that are actually in contact may form a ring or a partially ring-shaped collision area. In this case, the area where the tactile sensing units are located, which are completely surrounded by the ring area or partially surrounded by the partially ring area, can be selectively divided into the collision area S.

[0095] For example, Figure 4In the tactile sensing units 1, 2, 3, 4, 9, 10, and 12, if tactile sensing unit 1, 3, 4, 9, 10, and 12 are triggered while tactile sensing unit 2 is not triggered, the area where tactile sensing unit 2 is located can be directly designated as a potential danger zone within the collision zone S. Alternatively, if the average value of the sensing signals from the triggered tactile sensing units 1, 3, 4, 9, 10, and 12 is greater than a set threshold, the area where tactile sensing unit 2 is located can be designated as a potential danger zone within the collision zone S. The sensing signals of untriggered tactile sensing units can be considered as zero in subsequent calculations.

[0096] Furthermore, when the annular region or local annular region formed by the location of the triggered tactile sensing unit is large, the area enclosed by the annular region or local annular region containing the tactile sensing unit can be disregarded. For example... Figure 4 In this embodiment, when tactile sensing units 1 to 16, specifically 1, 3, 5, 7, 8, 16, 15, 13, 11, 10, and 9, are triggered while tactile sensing units 2, 4, 6, 12, and 14 are not triggered, the collision area S may exclude the area containing the untriggered tactile sensing units. Specifically, it can be determined whether to include the area containing the untriggered tactile sensing units within the collision area S based on the number of tactile sensing units surrounded by the area formed by the tactile sensing units that are actually triggered by touch. Based on the improved collision area S, the collision detection of this embodiment is more applicable to various practical application scenarios, improving the collision detection accuracy and the practicality and applicability of this embodiment.

[0097] The method of determining the collision state of the robotic arm based on the first average value of the sensing signals from two or more tactile sensing units within the collision area when touched can be expressed as follows: Calculate the first average value of the resultant force of the one-dimensional or multi-dimensional tactile pressure corresponding to the sensing signals collected by N tactile sensing units within the collision area S; use this first average value as the average collision force; and determine the collision state of the robotic arm based on the average collision force. The formula for calculating the first average value f is as follows:

[0098]

[0099] Additionally, the maximum value of the resultant force of one-dimensional or multi-dimensional tactile pressure corresponding to the sensing signals collected by the N tactile sensing units within the collision area S can also be obtained. The maximum value f max As the maximum collision force. The maximum value f max The corresponding tactile sensing unit is denoted as A, and the sensing signal collected by the tactile sensing unit adjacent to tactile sensing unit A within the collision area S is denoted as F. max (f j The induced signal F max (f j f is used to represent the tactile pressure vector collected by other triggered tactile sensing units adjacent to tactile sensing unit A. j This represents the sensing signal collected by the j-th tactile sensing unit among the other triggered tactile sensing units adjacent to tactile sensing unit A. This sensing signal can represent one-dimensional tactile pressure or the resultant force of multi-dimensional tactile pressure. j represents the number of the other triggered tactile sensing units adjacent to tactile sensing unit A, and j takes the value of an integer from 1 to M, where M represents the number of the other triggered tactile sensing units adjacent to tactile sensing unit A. For example, as... Figure 4 As shown, when tactile sensing unit 6 is tactile sensing unit A corresponding to the maximum value, the other triggered tactile sensing units adjacent to it can include tactile sensing units 4, 5, 7, 8, 14, and 16. The method of determining the collision state of the robotic arm based on the maximum value of the sensing signals from two or more tactile sensing units and the second average value of the sensing signals from the tactile sensing units adjacent to the maximum value can be expressed as follows: Calculate the second average value of the resultant force of the one-dimensional or multi-dimensional tactile pressure corresponding to the sensing signals collected by the other M triggered tactile sensing units adjacent to tactile sensing unit A, and use the second average value as the average collision force in the neighborhood; determine the collision state of the robotic arm based on the maximum collision force and the average collision force in the neighborhood. The formula for calculating the second average value f′ is expressed as follows:

[0100]

[0101] For example, the tactile sensing units adjacent to the tactile sensing unit corresponding to the maximum value may include triggered and adjacent tactile sensing units, and may also include untriggered and adjacent units; for example, when calculating the second average value corresponding to other tactile sensing units adjacent to tactile sensing unit A, the other tactile sensing units may also include untriggered and adjacent tactile sensing units to tactile sensing unit A.

[0102] For example, when tactile sensing unit 6 is the tactile sensing unit A corresponding to the maximum value, and its adjacent and triggered units are tactile sensing units 4, 5, 7, and 8, while its adjacent and untriggered units are tactile sensing units 14 and 16, then when calculating the second average value, the average value of all its adjacent tactile sensing units 4, 5, 7, 8, 14, and 16 can also be calculated; among them, the sensing signals of the untriggered tactile sensing units 14 and 16 can be considered as zero. Therefore, based on the improvement of the region adjacent to the location of the maximum collision force, it is more in line with actual application scenarios, improves the accuracy of collision detection, and reduces the probability of false positives.

[0103] In some embodiments, the controller is configured with a first collision detection condition and a second collision detection condition. When the sensing signal meets either the first or the second collision detection condition, it can be determined that the robotic arm is in a collision state. When the sensing signal does not meet either the first or the second collision detection condition, it is determined that the robotic arm is in a non-collision state. This allows for more accurate detection of the collision state based on the sensing signal of the tactile sensor, reducing the probability of misjudging the collision state and causing the robotic arm's movement to become invalid.

[0104] In some embodiments, when the first average value is greater than or equal to the first threshold δ1, the first collision detection condition is met, and the robotic arm is determined to be in a collision state; or, when the maximum value is greater than or equal to the second threshold δ2 and the second average value is greater than or equal to the third threshold δ3, the second collision detection condition is met, and the robotic arm is determined to be in a collision state; wherein, the second threshold δ2 is greater than the third threshold δ3.

[0105] In some embodiments, the first threshold δ1, the second threshold δ2, and the third threshold δ3 can be set according to the structure of the robotic arm and the actual application scenario, or the controller can be configured with multiple thresholds corresponding to different application scenarios. In practical applications, the thresholds can be switched according to different scenarios to select different collision detection conditions. The first collision detection condition and the second collision detection condition can be selectively configured according to actual needs.

[0106] In some embodiments, based on collision detection conditions, the controller can also identify different collision states and drive the robotic arm to execute obstacle avoidance movement modes based on the different collision states.

[0107] In some embodiments, the collision state includes a first collision state or a second collision state. The robot arm's collision state is determined to be the first collision state when the first average value f is greater than or equal to a first threshold δ1 and less than or equal to a fourth threshold δ4, or when the second average value f′ is greater than or equal to a third threshold δ3 and less than or equal to a fourth threshold δ4. The robot arm's collision state is determined to be the second collision state when the first average value f is greater than the fourth threshold δ4, or when the second average value f′ is greater than the fourth threshold δ4. The fourth threshold δ4 is greater than the first threshold δ1 and greater than the third threshold δ3; the fourth threshold δ4 can be set according to the robot arm's structure and the actual application scenario.

[0108] Based on the actual load-bearing capacity of the robotic arm, a maximum detection threshold, namely the fourth threshold δ4, is set for the tactile sensor. The relationship between the detected sensor signal and this fourth threshold δ4 is used to more accurately determine the robotic arm's collision state. For example, when the robotic arm contacts an obstacle in its current motion state, the tactile sensing unit of the triggered tactile sensor detects a signal that changes continuously in real time with the robotic arm's motion state, thus detecting the robotic arm's collision state.

[0109] In some embodiments, upon detecting a collision with the robotic arm, the robot will immediately take protective measures to reduce collision damage. Based on the collision detection conditions that trigger the collision state, a corresponding collision force measurement index is selected, and different levels of protective measures are adopted, i.e., different types of obstacle avoidance movement modes.

[0110] In some embodiments, the controller is configured with a collision avoidance function, which includes: if the robotic arm is in motion, driving the robotic arm to move according to a preset control mode based on a sensing signal and a collision state. The collision state includes a first collision state or a second collision state, and the preset control mode includes at least one of the following: a retraction control mode and an admittance control mode.

[0111] For example, when the robotic arm makes a contact during its movement, and provided that the collision detection condition that triggers the collision state is either the first collision detection condition or the second collision detection condition, the first average value f is approximated as the average and maximum collision force f. max Approximating the maximum collision force and the second average value of the neighborhood, f′ is approximated as the average collision force of the neighborhood. Different levels of protective measures are taken for different intervals, such as retreat control mode or admittance control mode.

[0112] In some embodiments, when the collision state is a first collision state, the robotic arm is driven to move according to the admittance control mode based on the sensing signal; when the collision state is a second collision state, the robotic arm is driven to move according to the retraction control mode based on the sensing signal.

[0113] In some embodiments, driving the robotic arm to move in an admittance control mode based on a sensing signal includes: determining the operating speed based on the sensing signal, and driving the robotic arm to move continuously at the operating speed in the admittance control mode until the robotic arm is no longer in the first collision state.

[0114] For example, determining the operating speed based on the sensing signal includes: reducing the operating speed of the robotic arm to a preset percentage D% of the original speed, wherein the preset percentage can be calculated based on the threshold range corresponding to the sensing signal, and the calculation formula is expressed as follows:

[0115]

[0116] in,

[0117] The following explanation is provided in conjunction with the accompanying drawings, such as... Figure 6 As shown in Figure (a), the original path of the robotic arm is from the first position A to the second position D. However, when the robotic arm moves from the first position A to the third position B along the original path, it is detected that the robotic arm is in the first collision state at the third position B. This triggers the admittance control mode of the robotic arm. At this time, the resultant force of the collision force on the robotic arm is determined based on the sensing signal of the tactile sensing unit. Based on this resultant force, the running speed is calculated using formula (3), and the robotic arm moves along the admittance control path to the fourth position C at this running speed, so that the robotic arm is not in the first collision state. The admittance control path can be planned based on the direction of the resultant force of the collision force and the position of the collision area. This embodiment does not limit the specific planning algorithm of the admittance control path. When the robotic arm moves in the admittance control mode, the posture of the end of the robotic arm may change or remain unchanged.

[0118] In some embodiments, driving the robotic arm to move in a reversal control mode based on a sensing signal includes: driving the robotic arm to move a preset step length along the displacement direction after the robotic arm is controlled to stop, based on the displacement direction determined by the sensing signal.

[0119] Exemplarily, when it is detected that the robotic arm is in the second collision state, the original speed of the robotic arm is reduced to zero to control the robotic arm to stop, and the robotic arm is driven to move a preset step length in the displacement direction determined based on the induction signal. The preset step length can be a pre-set value or can be adjusted according to the real-time induction signal. For example, the preset step length is determined according to the magnitude of the collision force characterized by the induction signal. Specifically, the preset step length can be positively correlated with the magnitude of the collision force. When executing the retraction control mode based on the induction signal, the posture of the robotic arm when it stops moving can be controlled to remain unchanged, and it moves a preset step length along the displacement direction. Among them, the displacement direction can be determined based on the induction signal of the triggered tactile sensing unit. For example, the resultant force of the collision force of the robotic arm is obtained based on the induction signal, and the displacement direction of the retraction control is determined according to the magnitude and direction of the resultant force.

[0120] The following will be described with reference to the accompanying drawings. As Figure 6 shown in figure (b) of Figure 6 When the robotic arm moves along the original movement direction to position ① and it is detected that the robotic arm is in the second collision state, the retraction control mode is triggered. Suppose the displacement direction determined based on the induction signal of the triggered tactile sensing unit at this time is the direction indicated by the arrow in the figure. Then, the robotic arm is controlled to stop moving and move in the determined displacement direction (suppose it moves to position ②). When executing the retraction control mode, the posture of the end of the robotic arm can be kept unchanged, and by rotating each axis of the robotic arm, the end of the robotic arm is linked to control to achieve the obstacle avoidance function of retraction.

[0121] In some embodiments, the controller is further configured with a touch teaching function, and the touch teaching function includes: if the robotic arm is in a stationary state, the robotic arm is driven to move in a preset teaching mode based on the induction signal.

[0122] Exemplarily, when the robotic arm is in a stationary state and is touched by the outside world, for example, when the user touches the stationary robotic arm by patting, pushing or pressing, etc., the tactile sensor can detect the induction signal, and the controller determines the motion parameters of the robotic arm corresponding to the teaching mode based on the induction signal, such as the motion direction and motion speed, and drives the robotic arm to move in the teaching mode based on the motion parameters.

[0123] Exemplarily, the preset teaching mode can include one or more of a position jog mode, a position linkage mode, an attitude jog mode, an attitude linkage mode or a position and attitude linkage mode.

[0124] Specifically, when the teaching mode is a position inching mode, driving the robotic arm to move based on the motion parameters in this mode may include: determining the displacement direction based on the sensing signal from the tactile sensor, maintaining the posture of the robotic arm's end effector unchanged, and driving the robotic arm's end effector to move a preset step length along the real-time determined displacement direction; when the teaching mode is a position linkage mode, driving the robotic arm to move based on the motion parameters in this mode may include: determining the displacement direction based on the sensing signal from the tactile sensor, maintaining the posture of the robotic arm's end effector unchanged, and driving the robotic arm's end effector to move continuously along the real-time determined displacement direction until the sensing signal from the tactile sensor is less than a preset signal value; when the teaching mode is a posture inching mode, driving the robotic arm to move based on the motion parameters in this mode may include: determining the rotation direction based on the sensing signals from tactile sensors in any two different areas ... and when the teaching mode is a posture inching mode, driving the robotic arm to move based on the motion parameters in this mode may include: determining the rotation direction based on the sensing signals from tactile sensors in any two different areas, maintaining the posture of the robotic arm's end effector unchanged, and driving the robotic arm's end effector to move continuously along the real-time determined displacement direction until the sensing signal from the tactile sensor is less than a preset signal value. The position of the end effector remains unchanged, and the end effector of the robotic arm is driven to rotate by a preset angle along a real-time determined rotation direction. When the teaching mode is the posture linkage mode, driving the robotic arm to move in this teaching mode based on the motion parameters may include: determining the rotation direction based on the sensing signals of tactile sensors in any two different areas, keeping the position of the end effector of the robotic arm unchanged, and driving the end effector of the robotic arm to continuously rotate along the real-time determined rotation direction until the sensing signal of any tactile sensor is less than a preset signal value. When the teaching mode is the position and posture linkage mode, driving the robotic arm to move in this teaching mode based on the motion parameters may include: determining the displacement direction and rotation direction based on the sensing signals of tactile sensors in any two different areas, and driving the end effector of the robotic arm to continuously move and rotate along the real-time determined displacement direction and rotation direction until the sensing signal of any tactile sensor is less than a preset signal value.

[0125] Correspondingly, the controller can also switch the teaching mode of the robotic arm based on mode switching commands. This embodiment realizes the teaching function through touch, which simplifies the use of the robotic arm. Tactile sensors have a certain price advantage over six-dimensional force sensors. Compared with the traditional drag teaching method based on six-dimensional force sensors, the solution of this application can reduce the production cost of the robotic arm to a certain extent and improve its applicability.

[0126] Another embodiment of this application also provides a collision detection method for a robotic arm, such as... Figure 7 As shown, the collision detection method for the robotic arm includes:

[0127] S701 determines the collision state of the robotic arm based on the sensing signals from the tactile sensor.

[0128] In this embodiment, the sensing signal is used to characterize the force information in at least one direction, and the tactile sensor can be set at the end of the robotic arm. Specifically, the method of the sensing signal characterizing the force information, the setting method of the tactile sensor, and the process of determining the collision state can be referred to the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0129] S702, if the robotic arm is in motion, the robotic arm is driven to move according to the preset control mode based on the above-mentioned sensing signals and the above-mentioned collision state.

[0130] In this embodiment, upon detecting a collision, the robot will immediately take protective measures via its controller to reduce collision damage. Based on the collision detection conditions that triggered the collision, a corresponding collision force measurement index (a threshold index of the collision force corresponding to the collision state) is selected, and different levels of protective measures are implemented.

[0131] In some embodiments, the tactile sensor includes a plurality of tactile sensing units, each of which generates a corresponding sensing signal when a corresponding area is touched; determining the collision state of the robotic arm based on the sensing signals of the tactile sensor includes: determining the collision state of the robotic arm based on the sensing signals of two or more tactile sensing units within the collision area when touched.

[0132] In one application scenario, determining the collision state of a robotic arm based on the sensing signals of two or more tactile sensing units within the collision area when touched includes: determining the collision state of the robotic arm based on a first average value of the sensing signals of two or more tactile sensing units.

[0133] In another application scenario, the collision state of the robotic arm is determined based on the sensing signals of two or more tactile sensing units within the collision area when it is touched, including: determining the collision state of the robotic arm based on the maximum value of the sensing signals of two or more tactile sensing units and the second average value of the sensing signals of the tactile sensing units adjacent to the maximum value.

[0134] In one implementation, determining the collision state of a robotic arm based on sensing signals from two or more tactile sensing units includes: when a first average value is greater than or equal to a first threshold, a first collision detection condition is met, and the robotic arm is determined to be in the collision state.

[0135] In another implementation, the collision state of the robotic arm is determined based on the sensing signals of two or more tactile sensing units, including: when the maximum value is greater than or equal to a second threshold and the second average value is greater than or equal to a third threshold, a second collision detection condition is met, and the robotic arm is determined to be in a collision state; wherein, the second threshold is greater than the third threshold.

[0136] Specifically, the calculation process and representation of the first average value, the maximum value, and the second average value can be referred to the description in the foregoing embodiments, and will not be repeated here.

[0137] In some embodiments, the collision state may include a first collision state or a second collision state; determining the collision state of the robotic arm based on sensing signals from two or more tactile sensing units may further include: determining the collision state of the robotic arm as the first collision state when a first average value is greater than or equal to a first threshold and less than or equal to a fourth threshold, or when a second average value is greater than or equal to a third threshold and less than or equal to a fourth threshold. Determining the collision state of the robotic arm as the second collision state when the first average value is greater than the fourth threshold, or when a second average value is greater than the fourth threshold. Wherein, the fourth threshold is greater than the first threshold and the fourth threshold is greater than the third threshold.

[0138] In some embodiments, the preset control mode may include at least one of the following: a retraction control mode and an admittance control mode. Driving the robotic arm to move according to the preset control mode based on the sensing signal and the collision state includes: when the collision state is a first collision state, driving the robotic arm to move according to the admittance control mode based on the sensing signal; and when the collision state is a second collision state, driving the robotic arm to move according to the retraction control mode based on the sensing signal.

[0139] In one embodiment, driving the robotic arm to move in an admittance control mode based on a sensing signal includes: determining the operating speed based on the sensing signal, and driving the robotic arm to move continuously at the operating speed in the admittance control mode until the robotic arm is no longer in the first collision state.

[0140] In one embodiment, driving the robotic arm to move in a reversal control mode based on a sensing signal includes: determining the displacement direction based on the sensing signal, and driving the robotic arm to move a preset step length along the displacement direction after controlling the robotic arm to stop.

[0141] As can be seen from the above, the method of placing a tactile sensor on a robotic arm and determining the collision state of the robotic arm based on the sensor's sensing signal can be applied to collision detection of both metallic and non-metallic obstacles, expanding the application range. Moreover, detecting the collision state based on the sensor's sensing signal can improve the accuracy of collision detection and facilitate timely determination of the collision state, thereby reducing the probability of impact injuries caused by collisions. This makes the robotic arm more convenient and cost-effective in practical applications.

[0142] S703: If the robotic arm is stationary, it will be driven to move in a preset teaching mode based on the sensing signal.

[0143] For example, when the robotic arm is stationary and is touched by the outside world, the tactile sensor can detect the sensing signal. The controller determines the motion parameters of the robotic arm in the teaching mode based on the sensing signal, such as the direction of motion and the speed of motion, and drives the robotic arm to move in the teaching mode based on the motion parameters.

[0144] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0145] For example, this application also provides a robotic arm, including: a tactile sensor, a memory, and a processor disposed on the robotic arm. The processor is used to read and execute a computer program stored in the memory to implement the steps of the above-described robotic arm collision detection method. For example, this application also provides a robot including the robotic arm.

[0146] For example, this application also provides a chip including a processor, which is used to read and execute a computer program stored in a memory to implement the steps of the above-described robotic arm collision detection method.

[0147] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0148] 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 method. 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.

[0149] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. Furthermore, integrated modules / units, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in computer-readable media may be appropriately added to or subtracted from the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, computer-readable media may not include electrical carrier signals and telecommunication signals, in accordance with legislation and patent practice.

[0150] The above embodiments are only used to illustrate the system and method of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the method solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the method features. Such modifications or substitutions do not cause the essence of the corresponding method solutions to deviate from the spirit and scope of the method solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A robot collision detection system, characterized by, The method comprises: a tactile sensor arranged on a mechanical arm; and a controller connected with the tactile sensor; the controller is configured with a collision detection function, the collision detection function comprises: determining the collision state of the mechanical arm based on the sensing signal of the tactile sensor, the sensing signal is used to represent the force information in at least one direction; wherein the tactile sensor forms a tactile sensing area including a plurality of tactile sensing units, each tactile sensing unit generates a corresponding sensing signal when the corresponding tactile sensing area is touched; the sensing signal includes one-dimensional tactile pressure or multi-dimensional tactile pressure; determining the collision state of the mechanical arm based on the sensing signal of the tactile sensor comprises: calculating a first average value or a second average value based on the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure collected by the tactile sensing units in the collision area and the number of the tactile sensing units; determining the collision state according to the size relationship between the first average value and the collision force measurement index, or the size relationship between the second average value and the collision force measurement index; the collision force measurement index is a threshold index corresponding to the collision state; wherein the first average value is the collision force average value of the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure collected by N tactile sensing units in the collision area; the tactile sensing unit corresponding to the maximum collision force is recorded as A, and the second average value is the neighborhood collision force average value of the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure corresponding to the sensing signal collected by the other M triggered tactile sensing units adjacent to the tactile sensing unit A.

2. The system of claim 1, wherein, The tactile sensor includes a plurality of tactile sensing units, each tactile sensing unit generates a corresponding sensing signal when the corresponding area is touched; The determination of the collision state of the mechanical arm based on the sensing signal of the tactile sensor is: determining the collision state of the mechanical arm based on the sensing signal of two or more tactile sensing units in the collision area when touched.

3. The system of claim 2, wherein, The determination of the collision state of the mechanical arm based on the sensing signal of the two or more tactile sensing units in the collision area when touched comprises: determining the collision state of the mechanical arm based on the first average value of the sensing signal of the two or more tactile sensing units; or determining the collision state of the mechanical arm based on the maximum value of the sensing signal of the two or more tactile sensing units and the second average value of the sensing signal of the tactile sensing units adjacent to the tactile sensing unit corresponding to the maximum value.

4. The system of claim 3, wherein, The controller is configured with a first collision detection condition and a second collision detection condition; The determination of the collision state of the mechanical arm based on the sensing signal of the two or more tactile sensing units comprises: when the first average value is greater than or equal to a first threshold value, the first collision detection condition is met, and it is determined that the mechanical arm is in the collision state; or when the maximum value is greater than or equal to a second threshold value and the second average value is greater than or equal to a third threshold value, the second collision detection condition is met, and it is determined that the mechanical arm is in the collision state; wherein the second threshold value is greater than the third threshold value. The first threshold value, the second threshold value and the third threshold value are threshold values set based on the structure of the robot arm and actual application scenarios.

5. The system of claim 4, wherein, The collision state includes a first collision state or a second collision state. The determination of the collision state of the robot arm based on the sensing signals of the two or more tactile sensing units includes: When the first average value is greater than or equal to the first threshold value and less than or equal to a fourth threshold value, or when the second average value is greater than or equal to the third threshold value and less than or equal to the fourth threshold value, the collision state of the robot arm is determined as the first collision state. When the first average value is greater than the fourth threshold value, or when the second average value is greater than the fourth threshold value, the collision state of the robot arm is determined as the second collision state. The fourth threshold value is greater than the first threshold value, and the fourth threshold value is greater than the third threshold value. The fourth threshold value is a collision force measurement index set based on the load capacity of the robot arm.

6. The system of claim 2, wherein, The tactile sensor is arranged on the outer surface of the robot arm, and the tactile sensing units are arranged in an array on the outer surface of the robot arm.

7. The system according to any of claims 1 to 4, 6, characterized in that, The controller is configured with a collision avoidance function, and the collision avoidance function includes: if the robot arm is in a motion state, driving the robot arm to move in a preset control mode based on the sensing signals and the collision state.

8. The system of claim 5, wherein, The controller is configured with a collision avoidance function, and the collision avoidance function includes: if the robot arm is in a motion state, driving the robot arm to move in a preset control mode based on the sensing signals and the collision state.

9. The system of claim 8, wherein, The preset control mode includes at least one of the following: a fallback control mode and an admittance control mode. The driving of the robot arm to move in the preset control mode based on the sensing signals and the collision state includes: When the collision state is the first collision state, driving the robot arm to move in the admittance control mode based on the sensing signals; When the collision state is the second collision state, driving the robot arm to move in the fallback control mode based on the sensing signals.

10. The system of claim 9, wherein, The driving of the robot arm to move in the admittance control mode based on the sensing signals includes: Determining a running speed based on the sensing signals, and driving the robot arm to continuously move at the running speed in the admittance control mode until the robot arm is not in the first collision state; The driving of the robot arm to move in the fallback control mode based on the sensing signals includes: Determining a displacement direction, and driving the robot arm to move in the displacement direction by a preset step length after the robot arm is controlled to stop. The determination of the running speed based on the sensing signals includes: Determining a threshold value interval corresponding to the sensing signals based on a first collision detection condition and a second collision detection condition; Calculating a preset percentage based on the threshold value interval corresponding to the sensing signals; Reducing the running speed of the robot arm to a preset percentage of the original speed.

11. The system of any one of claims 1 to 6, wherein, The controller is configured with a touch teaching function, and the touch teaching function includes: if the robot arm is in a static state, driving the robot arm to move in a preset teaching mode based on the sensing signal.

12. A method of collision detection for a robotic arm, the method comprising: Comprise: Determine the collision state of the robot arm based on the sensing signal of the tactile sensor, the sensing signal is used to represent the force information in at least one direction, and the tactile sensor is arranged on the robot arm; Wherein, the tactile sensor forms a tactile sensing area including a plurality of tactile sensing units, each tactile sensing unit generates a corresponding sensing signal when the corresponding tactile sensing area is touched; the sensing signal includes one-dimensional tactile pressure or multi-dimensional tactile pressure; determining the collision state of the robot arm based on the sensing signal of the tactile sensor, comprising: Based on the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure collected by the tactile sensing units in the collision area and the number of the tactile sensing units, a first average value or a second average value is calculated; According to the size relationship between the first average value and the collision force measurement index, or the size relationship between the second average value and the collision force measurement index, the collision state is determined; the collision force measurement index is a threshold index corresponding to the collision state; wherein the first average value is the collision force average value of the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure collected by the N tactile sensing units in the collision area; the tactile sensing unit corresponding to the maximum collision force is recorded as A, and the second average value is the neighborhood collision force average value of the one-dimensional tactile pressure or the multi-dimensional tactile pressure corresponding to the sensing signal collected by the other M triggered tactile sensing units adjacent to the tactile sensing unit A.

13. The method of claim 12, wherein, The tactile sensor includes a plurality of tactile sensing units, each tactile sensing unit generates a corresponding sensing signal when the corresponding area is touched; The determination of the collision state of the robot arm based on the sensing signal of the tactile sensor comprises: Determine the collision state of the robot arm based on the sensing signal of two or more tactile sensing units in the collision area when touched.

14. The method of claim 13, wherein, The determination of the collision state of the robot arm based on the sensing signal of two or more tactile sensing units in the collision area when touched comprises: Determine the collision state of the robot arm based on the first average value of the sensing signal of the two or more tactile sensing units; or, Determine the collision state of the robot arm based on the maximum value of the sensing signal of the two or more tactile sensing units and the second average value of the sensing signal of the tactile sensing units adjacent to the tactile sensing unit corresponding to the maximum value.

15. The method of claim 14, wherein, The determination of the collision state of the robot arm based on the sensing signal of the two or more tactile sensing units comprises: When the first average value is greater than or equal to a first threshold value, the first collision detection condition is met, and it is determined that the robot arm is in the collision state; or, When the maximum value is greater than or equal to a second threshold value and the second average value is greater than or equal to a third threshold value, the second collision detection condition is met, and it is determined that the robot arm is in the collision state; wherein the second threshold value is greater than the third threshold value; The first threshold value, the second threshold value and the third threshold value are threshold values set based on a structure of the robot arm and an actual application scenario.

16. The method of claim 15, wherein, The collision state includes a first collision state or a second collision state. The determining of the collision state of the robot arm based on the sensing signals of the two or more tactile sensors includes: When the first average value is greater than or equal to the first threshold value and less than or equal to a fourth threshold value, or when the second average value is greater than or equal to the third threshold value and less than or equal to the fourth threshold value, the collision state of the robot arm is determined as the first collision state; When the first average value is greater than the fourth threshold value, or when the second average value is greater than the fourth threshold value, the collision state of the robot arm is determined as the second collision state; The fourth threshold value is greater than the first threshold value, and the fourth threshold value is greater than the third threshold value. The fourth threshold value is a collision force measurement index set based on a load capacity of the robot arm.

17. The method of any one of claims 12 to 15, wherein, After the collision state of the robot arm is determined based on the sensing signals of the tactile sensors, the method further includes: If the robot arm is in a motion state, the robot arm is driven to move in a preset control mode based on the sensing signals and the collision state.

18. The method of claim 16, wherein, After the collision state of the robot arm is determined based on the sensing signals of the tactile sensors, the method further includes: If the robot arm is in a motion state, the robot arm is driven to move in a preset control mode based on the sensing signals and the collision state.

19. The method of claim 18, wherein, The collision state includes a first collision state or a second collision state, and the preset control mode includes at least one of a fallback control mode and an admittance control mode. The driving of the robot arm to move in the preset control mode based on the sensing signals and the collision state includes: When the collision state is the first collision state, the robot arm is driven to move in the admittance control mode based on the sensing signals; When the collision state is the second collision state, the robot arm is driven to move in the fallback control mode based on the sensing signals.

20. The method of claim 19, wherein, The driving of the robot arm to move in the admittance control mode based on the sensing signals includes: A running speed is determined based on the sensing signals, and the robot arm is driven to continuously move at the running speed in the admittance control mode until the robot arm is not in the first collision state; The driving of the robot arm to move in the fallback control mode based on the sensing signals includes: A displacement direction is determined based on the sensing signals, and the robot arm is driven to move in the displacement direction by a preset step length after the robot arm is controlled to stop. The determination of the running speed based on the sensing signals includes: A threshold value interval corresponding to the sensing signals is determined based on a first collision detection condition and a second collision detection condition; A preset percentage is calculated based on the threshold value interval corresponding to the sensing signals; A running speed of the robot arm is reduced to a preset percentage of an original speed.

21. The method of any one of claims 12 to 16, wherein, After the collision state of the robot arm is determined based on the sensing signals of the tactile sensors, the method further includes: If the robot arm is in a motion state, the robot arm is driven to move in a preset control mode based on the sensing signals and the collision state. If the robot arm is in a static state, driving the robot arm to move in a preset teaching mode based on the sensing signal.

22. A robotic arm, comprising: Comprising: A tactile sensor, a memory and a processor disposed on the robot arm, the processor being configured to read and execute a computer program stored in the memory to implement the steps of the method of any one of claims 19-21.

23. A robot, characterized in that Comprising: The robot arm of claim 22.

24. A chip, characterized by A processor configured to read and execute a computer program stored in the memory to implement the steps of the method of any one of claims 12-21.

Images