CN115351818A

CN115351818A - Mechanical arm collision detection system and method, mechanical arm, robot and chip

Info

Publication number: CN115351818A
Application number: CN202211014768.5A
Authority: CN
Inventors: 赵丹; 黄睿; 郎需林; 姜宇
Original assignee: Shenzhen Yuejiang Technology Co Ltd
Current assignee: Shenzhen Yuejiang Technology Co Ltd
Priority date: 2022-08-23
Filing date: 2022-08-23
Publication date: 2022-11-18

Abstract

The application belongs to the technical field of mechanical arms and provides a system, a method, a mechanical arm, a robot and a chip for detecting mechanical arm collision, wherein the system for detecting mechanical arm collision comprises a touch sensor arranged on the mechanical arm; and a controller connected to the tactile sensor; the controller is configured with a collision detection function including: and determining the collision state of the mechanical arm based on the sensing signals of the touch sensor, wherein the sensing signals are used for representing the stress information in at least one direction. The technical scheme that this application provided can effectively improve collision detection precision, reduce the probability of collision injury.

Description

Mechanical arm collision detection system and method, mechanical arm, robot and chip

Technical Field

The application belongs to the technical field of mechanical arms, and particularly relates to a mechanical arm collision detection system, a mechanical arm collision detection method, a mechanical arm, a robot and a chip.

Background

Collision detection is an important technical means for robot safety control. At present, a common robot arm collision detection method mainly includes a contact type collision detection method based on a current loop.

However, in the contact type collision detection method based on the current loop, since the change of the joint current caused by detecting the collision torque, the detection precision is low, and the collision damage is easily caused.

Disclosure of Invention

The embodiment of the application provides a mechanical arm collision detection system, a mechanical arm collision detection method, a mechanical arm, a robot and a chip, and can improve collision detection precision and reduce collision damage probability.

In a first aspect, the present application provides a robot arm collision detection system, including:

a touch sensor arranged on the mechanical arm;

and a controller connected to the tactile sensor;

the controller is configured with a collision detection function including: and determining the collision state of the mechanical arm based on the sensing signals of the touch sensor, wherein the sensing signals are used for representing the stress information in at least one direction.

According to the first aspect of the present application, in a first possible implementation manner, the touch sensor includes a plurality of touch sensing units, each of which generates a corresponding sensing signal when a corresponding region is touched;

the determining of the collision state of the mechanical arm based on the sensing signal of the touch sensor comprises: and determining the collision state of the mechanical arm based on the sensing signals of more than two touch sensing units in the collision area when the mechanical arm is touched.

Based on the first possible implementation manner of the first aspect of the present application, in a second possible implementation manner, the determining a collision state of the robot arm based on sensing signals of two or more tactile sensing units in a collision region when the robot arm is touched includes:

determining a collision state of the mechanical arm based on a first average value of sensing signals of the more than two touch sensing units; alternatively, the first and second electrodes may be,

and determining the collision state of the mechanical arm based on the maximum value of the induction signals of the more than two touch induction units and the second average value of the induction signals of the adjacent touch induction units of the touch induction unit corresponding to the maximum value.

Based on the second possible implementation manner of the first aspect of the present application, in a third possible implementation manner, the controller is configured with a first collision detection condition and a second collision detection condition;

the determining the collision state of the mechanical arm based on the sensing signals of the two or more touch 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 the mechanical arm is determined to be in the collision state; alternatively, the first and second liquid crystal display panels may be,

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 the mechanical arm is determined to be in the collision state; wherein the second threshold is greater than the third threshold.

Based on the third possible implementation manner of the first aspect of the present application, in a fourth possible implementation manner, the collision status includes a first collision status or a second collision status;

determining that the collision state of the robot arm is the first collision state 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;

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, determining that the collision state of the mechanical arm is the second collision state;

wherein the fourth threshold is greater than the first threshold, and the fourth threshold is greater than the third threshold.

Based on the first possible implementation manner of the first aspect of the present application, in a fifth possible implementation manner, the tactile sensor is disposed on the outer surface of the mechanical arm, and the tactile sensing units are arranged in an array on the outer surface of the mechanical arm.

Based on any one of the possible implementation manners of the first aspect of the present application, in a sixth possible implementation manner, the controller is configured with a collision avoidance function, where the collision avoidance function includes: and if the mechanical arm is in a motion state, driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state.

Based on the sixth possible implementation manner of the first aspect of the present application, in a seventh possible implementation manner, the collision status includes a first collision status or a second collision status, and the preset control mode includes at least one of the following: a fallback control mode and an admittance control mode;

the driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state comprises the following steps:

when the collision state is the first collision state, driving the mechanical arm to move in the admittance control mode based on the induction signal;

and when the collision state is the second collision state, driving the mechanical arm to move according to the retraction control mode based on the induction signal.

Based on the seventh possible implementation manner of the first aspect of the present application, in an eighth possible implementation manner, the driving the mechanical arm to move in the admittance control mode based on the sensing signal includes:

determining an operation speed based on the induction signal, and driving the mechanical arm to continuously move at the operation speed in the admittance control mode until the mechanical arm is not in the first collision state;

the driving the mechanical arm to move in the backspacing control mode based on the induction signal comprises the following steps:

and determining a displacement direction based on the induction signal, and driving the mechanical arm to move for a preset step length along the displacement direction after controlling the mechanical arm to stop.

Based on any one of the possible implementation manners of the first aspect of the present application, in a ninth possible implementation manner, the controller is configured with a touch teaching function, where the touch teaching function includes: and if the mechanical arm is in a static state, driving the mechanical arm to move in a preset teaching mode based on the induction signal.

In a second aspect, an embodiment of the present application provides a method for detecting a collision of a robot arm, including:

determining a collision state of the mechanical arm based on a sensing signal of a touch sensor, wherein the sensing signal is used for representing stress information in at least one direction, and the touch sensor is arranged on the mechanical arm.

According to the second aspect of the present application, in a first possible implementation manner, the touch sensor includes a plurality of touch sensing units, each of which generates a corresponding sensing signal when a corresponding region is touched;

the determining the collision state of the mechanical arm based on the sensing signal of the touch sensor comprises:

and determining the collision state of the mechanical arm based on the sensing signals of more than two touch sensing units in the collision area when the mechanical arm is touched.

Based on the first possible implementation manner of the second aspect of the present application, in a second possible implementation manner,

the determining the collision state of the mechanical arm based on the sensing signals of the more than two touch sensing units comprises:

determining a collision state of the mechanical arm based on a first average value of sensing signals of the more than two touch sensing units; alternatively, the first and second liquid crystal display panels may be,

and determining the collision state of the mechanical arm based on the maximum value of the sensing signals of the more than two touch sensing units and the second average value of the sensing signals of the touch sensing units adjacent to the touch sensing unit corresponding to the maximum value.

Based on the second possible implementation manner of the second aspect of the present application, in a third possible implementation manner,

when the first average value is greater than or equal to a first threshold value, a first collision detection condition is met, and the mechanical arm is determined to be in the collision state; alternatively, the first and second electrodes may be,

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, a second collision detection condition is met, and the mechanical arm is determined to be in the collision state; wherein the second threshold is greater than the third threshold.

Based on the third possible implementation manner of the second aspect of the present application, in a fourth possible implementation manner,

the collision state comprises a first collision state or a second collision state;

In a fifth possible implementation manner, based on any one of the possible implementation manners of the second aspect of the present application, after determining the collision state of the mechanical arm based on the sensing signal of the touch sensor, the method further includes:

and if the mechanical arm is in a motion state, driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state.

Based on the fifth possible implementation manner of the second aspect of the present application, in a sixth possible implementation manner, the collision status includes a first collision status or a second collision status, and the preset control mode includes at least one of the following: a fallback control mode and an admittance control mode;

the driving the mechanical arm to move according to a preset control mode based on the sensing signal and the collision state comprises:

and when the collision state is the second collision state, driving the mechanical arm to move in the backspacing control mode based on the induction signal.

In a seventh possible implementation manner according to the sixth possible implementation manner of the second aspect of the present application, the driving the mechanical arm to move in the admittance control mode based on the sensing signal includes:

determining a running speed based on the induction signal, and driving the mechanical arm to continuously move at the running speed in the admittance control mode until the mechanical arm is not in the first collision state;

In an eighth possible implementation manner of the second aspect of the present application, after determining the collision state of the mechanical arm based on the sensing signal of the touch sensor, the method further includes:

and if the mechanical arm is in a static state, driving the mechanical arm to move in a preset teaching mode based on the induction signal.

In a third aspect, the present application provides a robotic arm comprising a tactile sensor disposed on the robotic arm, a memory, and a processor configured to read and execute a computer program stored in the memory to implement the steps of the method of the second aspect.

In a fourth aspect, embodiments of the present application provide a robot, including the robot arm of the third aspect.

In a fifth aspect, the present application provides a chip, which includes a processor, and the processor is configured to read and execute a computer program stored in a memory to implement the steps of the method of the second aspect.

As can be seen from the above, in the present application, the tactile sensor is disposed on the mechanical arm, and the collision state of the mechanical arm is determined based on the sensing signal of the tactile sensor; because the contact type collision detection of the current loop is realized by detecting the change of joint current caused by collision moment, the detection precision is low and misjudgment is easy to occur; according to the method, the collision state is detected based on the sensing signals of the touch sensor, and when the mechanical arm collides, the stress information in at least one direction can be detected, so that the collision detection precision can be improved, the collision state can be determined in time conveniently, the probability of collision injury caused by collision can be reduced, and the mechanical arm is more convenient and lower in cost in the practical application process; has stronger usability and practicability.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

FIG. 1 is a schematic structural diagram of a collision detection system provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of an arrangement of a tactile sensor according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of another tactile sensor arrangement provided by embodiments of the present application;

FIG. 4 is a schematic layout diagram of the tactile sensing units of the tactile sensing area provided by the embodiment of the present application;

FIG. 5 is a schematic view of a scene with different collision states according to an embodiment of the present disclosure;

fig. 6 is a schematic view of an application scenario of mechanical arm collision detection provided in an embodiment of the present application;

fig. 7 is a schematic flow chart of a mechanical arm collision detection method according to an embodiment of the present application.

Detailed Description

In order to make the objects, methods, and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

"and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more (i.e., two or more) and "at least one", "one or more" means one, two or more unless otherwise specified.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

At present, a mechanical arm collision detection method of a robot mainly comprises contact type collision detection based on a current loop, however, the detection mode needs larger external force to enable the current loop to detect through detecting joint current change caused by collision torque, and the specific size of the larger external force cannot be determined, so that the collision detection precision is low, and the problems of mechanical arm collision contact damage or high-speed misjudgment failure and the like are easily caused.

Based on the above problems, the present application provides detailed descriptions of a robot arm collision detection system and specific embodiments thereof.

FIG. 1 illustrates a robotic arm collision detection system in one embodiment, comprising: a tactile sensor 101 provided to the robot arm, and a controller 102 connected to the tactile sensor 101. Wherein the controller 102 is configured with collision detection functionality including: the collision state of the robot arm is determined based on the sensing signal of the tactile sensor 101, which may represent force information in at least one direction. The collision state can be the state that the arm was in when touchhing the barrier in the operation process, confirms the motion state that the collision state can be convenient for follow-up to the arm through the inductive signal and controls, avoids causing the striking injury. The touch sensor is arranged on the mechanical arm, and in the motion process of the mechanical arm, the collision state of the mechanical arm is detected based on the sensing signal of the touch sensor, so that the method and the device can be suitable for detecting the collision of various barriers such as metal or nonmetal and the like, and the application range is greatly expanded; because the sensing signal can represent the stress information in at least one direction, the collision state can be conveniently and timely determined, the collision detection precision is improved, the probability of collision misjudgment and other problems is reduced, and the probability of collision damage caused by collision is reduced, so that the mechanical arm is more convenient and lower in cost in the practical application process.

In some embodiments, the controller may be disposed inside the robotic arm, or alternatively, may be disposed outside the robotic arm and may be in communication with the tactile sensor, directly or indirectly.

In some embodiments, as shown in fig. 2, the touch sensor may be attached to a surface of the end of the mechanical arm, and when an object (e.g., an obstacle) contacts the end of the mechanical arm, a corresponding sensing signal is generated, and the sensing signal is used to trigger the controller to drive the mechanical arm to perform a corresponding motion, for example, determine a collision state of the mechanical arm based on the magnitude of the sensing signal, and then drive the mechanical arm to stop moving, or reduce the moving speed, etc. It should be understood that, on one hand, attaching the touch sensor to the surface of the end of the mechanical arm does not limit the touch sensor to be exposed on the surface of the end of the mechanical arm, in practical applications, after attaching the touch sensor to the end of the mechanical arm, a protective layer or a protective shell may be further disposed on the outer layer to protect the touch sensor, and the disposition of the protective layer or the protective shell is restricted by not affecting the sensing accuracy of the touch sensor; on the other hand, as shown in fig. 2 and 3, the tactile sensor may be completely covered on the outer surface of the robot arm or partially covered on the outer surface of the robot arm, and may be specifically configured according to the structural shape of the robot to which the robot arm belongs.

For example, the sensor may be disposed at other positions of the robot arm, and the principle of being triggered and controlled for different positions is the same as that of the embodiment of the present application.

In some embodiments, the robot arm may determine the collision state according to the difference of the sensing signals, and drive the robot arm to perform corresponding movement based on the different collision states. For a multi-axis robot arm (e.g., a six-axis robot arm), in practical applications, the end of the robot arm may need to perform multiple degrees of freedom motions (e.g., perform linear motions along the X, Y, or Z axes), and for this purpose, the tactile sensor in this embodiment may be a tactile sensor (e.g., a piezoresistive tactile sensor, a piezoelectric tactile sensor, etc.) that detects a three-directional force, and such a tactile sensor may detect a three-directional force along the X, Y, and Z axes and generate a sensing signal with richer information. On the basis, corresponding collision conditions and motion parameters are configured for various sensing signals, so that the controller can drive the mechanical arm to execute a corresponding motion mode based on the collision state of the mechanical arm, the barrier avoiding function of the mechanical arm is realized timely and accurately, and the probability of collision damage of the mechanical arm is reduced.

In some embodiments, a tactile sensor is disposed on an outer surface of the robotic arm forming a tactile sensing region. As shown in fig. 2, a ring-shaped tactile sensor 101 may be provided at the end of the robot arm (the inner part of the circle is a close-up view of the end of the robot arm in the figure); fig. 3 shows a schematic diagram of two tactile sensors 101 disposed at the end of the robotic arm (a close-up view of the end of the robotic arm is shown within the circle).

In some embodiments, the robot arm collision detection system includes a tactile sensor disposed at an end of the robot arm, and the tactile sensor may include a plurality of tactile sensing units, each of which generates a corresponding sensing signal when a corresponding location is touched; one or more of the following information can be identified based on the sensing signal generated by the tactile sensor in real time: the position of the triggered touch sensing units in the trigger sensing area and the number of the triggered touch sensing units in real time. Illustratively, the differentiation of the tactile sensing areas may be achieved by hardware and/or software configuration, and the like. For a hardware mode, the method can be realized by arranging more than two touch sensors at the tail end of a mechanical arm; in a specific application, more than two touch sensors may be distributed on different planes to form more than two differentiated touch sensing areas, for example, fig. 3 shows a schematic diagram of two touch sensors 101 disposed at the end of the robot arm, and certainly, four touch sensors may also be disposed at the end of the robot arm, and the specific number of the touch sensors may be set according to the structural features of the robot arm. For the software configuration mode, the touch sensing area of the same touch sensor can be divided, so that the touch sensing area of the touch sensor is divided into more than two relatively independent touch sensing areas, namely more than two distinguished touch sensing areas are formed; as shown in fig. 2, a ring-shaped tactile sensor 101 may be provided at the end of the arm, and the tactile sensing area of the tactile sensor may be divided into two or more tactile sensing areas. The present embodiment does not limit the number of tactile sensors.

In some embodiments, the touch sensor includes a plurality of touch sensing units in the touch sensing area, each touch sensing unit generating a corresponding sensing signal when the corresponding touch sensing area is touched; and determining the collision state of the mechanical arm based on the sensing signals of the more than two touch sensing units in the collision area when the mechanical arm is touched. As shown in fig. 4, the tactile sensation units are arranged in an array form in the tactile sensation area, such as an arrangement form of a plurality of rows formed by the tactile sensation units 1 to 16.

It should be noted that fig. 4 is only an example, and the arrangement manner of the tactile sensation units on the outer surface of the mechanical arm is not particularly limited, and may be another layout form based on the arrangement of the structural features of the outer surface of the mechanical arm.

In some embodiments, the tactile sensor may detect tactile pressure in at least one dimension; the sensing signal generated by each touch sensing unit when being touched can represent the touch pressure corresponding to the direction of the coordinate axis. Or, the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure corresponding to each tactile sensing unit can be obtained according to the sensing signal; x as shown in FIG. 5 ₁ 、y ₁ And z ₁ Tactile pressure in three directions of the axis, or x ₂ 、y ₂ And z ₂ Three-directional tactile forces, or a resultant of three-directional tactile pressures each corresponding to the three-directional tactile forces.

In some embodiments, determining the collision state of the robot arm based on the sensing signals of the two or more tactile sensing units includes: determining the collision state of the mechanical arm based on a first average value of sensing signals of more than two touch sensing units in a collision area when the mechanical arm is touched; or determining the collision state of the mechanical arm based on the maximum value of the sensing signals of more than two touch sensing units and the second average value of the sensing signals of the touch sensing units adjacent to the touch sensing unit corresponding to the maximum value.

For example, the collision region S can be determined based on the positions of the tactile sensing units generating sensing signals in real time, and the collision region S includes the positions of N tactile sensing units (N is not less than 2) generating sensing signals in real time. With F (F) _i ) A tactile pressure vector that may represent a sensed signal detected in the collision region S; f. of _i The touch sensing unit number is the number of the touch sensing unit in the collision area S, and each numbered touch sensing unit canI can be an integer from 1 to N, corresponding uniquely to a certain position on the outer surface of the mechanical arm.

On one hand, the collision area S is an area formed by positions of all the tactile sensing units triggered to generate sensing signals; on the other hand, based on the specific structure of the obstacle, the tactile sensation units that are actually contacted may form an annular or partially annular collision region, and in this case, the region where the tactile sensation units are located, which is completely surrounded by the annular region or partially surrounded by the partially annular region, may be selectively divided into the collision region S.

For example, in the tactile sensing units 1, 2, 3, 4, 9, 10, 12 in fig. 4, when the tactile sensing units 1, 3, 4, 9, 10, 12 are triggered and the tactile sensing unit 2 is not triggered, the location area where the tactile sensing unit 2 is located can be directly classified as a potential danger zone into the collision area S; or when the average value of the sensing signals of the triggered tactile sensing units 1, 3, 4, 9, 10, 12 is greater than the set threshold, the position area where the tactile sensing unit 2 is located is classified as a potential danger zone into the collision area S. When the tactile sensing units 1, 3, 9, 10 and 12 are triggered and the tactile sensing unit 2 is not triggered, the position area where the tactile sensing unit 2 is located can be directly classified as a potential danger zone into the collision area S; or when the average value of the sensing signals of the triggered tactile sensing units 1, 3, 9, 10 and 12 is greater than the set threshold, the position area where the tactile sensing unit 2 is located is classified as a potential danger zone into the collision area S. Wherein, the sensing signal of the touch sensing unit which is not triggered can be regarded as zero in the subsequent calculation process.

In addition, when the annular area or the local annular area formed by the location of the triggered tactile sensing unit is larger, the area where the tactile sensing unit surrounded by the annular area or the local annular area is located may not be considered, for example, in fig. 4, when 1, 3, 5, 7, 8, 16, 15, 13, 11, 10, 9 of the tactile sensing units 1 to 16 is triggered, and the

tactile sensing units

2, 4, 6, 12, 14 are not triggered, the collision area S may not include the area where the tactile sensing unit that is not triggered is located, and specifically, based on the number of tactile sensing units surrounded by the area where the tactile sensing unit that is triggered actually generates a touch, it may be determined whether to divide the area where the surrounded and not triggered tactile sensing unit is located into the collision area S; based on the perfection of the collision region S, the collision detection of the embodiment of the application is more suitable for various different practical application scenes, and the practicability and the applicability of the embodiment of the application are improved while the collision detection precision is improved.

The determining of the collision state of the mechanical arm based on the first average value of the sensing signals of the two or more tactile sensing units in the collision region when being touched may be represented as: and calculating a first average value of resultant force of one-dimensional tactile pressure or multi-dimensional tactile pressure corresponding to the sensing signals acquired by the N tactile sensing units in the collision area S, taking the first average value as a collision force average value, and determining the collision state of the mechanical arm according to the collision force average value. Wherein, the formula for calculating the first average value f is expressed as follows:

in addition, the maximum value of the resultant force of the one-dimensional tactile pressure or the multi-dimensional tactile pressure corresponding to the sensing signal acquired by the N tactile sensing units in the collision region S can also be acquired

Will maximum value f _max As the maximum impact force. Will maximum value f _max The corresponding touch sensing unit is marked as A, and the sensing signal collected by the touch sensing unit adjacent to the touch sensing unit A in the collision area S is marked as F _max (f _j ) The induction signal F _max (f _j ) For representing the tactile pressure vectors, f, collected by other triggered tactile sensing units adjacent to the tactile sensing unit A _j The induction signal is acquired by the jth tactile induction unit in other triggered tactile induction units adjacent to the tactile induction unit A, and the induction signal can represent one-dimensional tactile pressure or multi-dimensional tactile pressureJ represents the number of other triggered tactile sensing units adjacent to the tactile sensing unit a, j takes an integer from 1 to M, and M represents the number of other triggered tactile sensing units adjacent to the tactile sensing unit a. For example, as shown in fig. 4, when the tactile sensing unit 6 is the tactile sensing unit a corresponding to the maximum value, other triggered tactile sensing units adjacent thereto may include

tactile sensing units

4, 5, 7, 8, 14, and 16. The determining of the collision state of the mechanical arm based on the maximum value of the sensing signals of the two or more tactile sensing units and the second average value of the sensing signals of the tactile sensing units adjacent to the tactile sensing unit corresponding to the maximum value may be as follows: calculating a second average value of resultant force of one-dimensional tactile pressure or multi-dimensional tactile pressure corresponding to sensing signals acquired by other M triggered tactile sensing units adjacent to the tactile sensing unit A, and taking the second average value as a neighborhood collision force average value; and determining the collision state of the mechanical arm according to the maximum value of the collision force and the mean value of the collision forces in the neighborhood. Wherein the formula for calculating the second average value f' is as follows:

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 further include un-triggered and adjacent units; for example, when calculating the second average value corresponding to the other tactile sensation units adjacent to the tactile sensation unit a, the other tactile sensation units may further include the tactile sensation unit adjacent to the tactile sensation unit a that is not triggered.

For example, when the tactile sensing unit a corresponding to the maximum tactile sensing unit 6 is the tactile sensing unit a adjacent to and triggered to be the

tactile sensing units

4, 5, 7 and 8 and adjacent to and not triggered to be the

tactile sensing units

14 and 16, then when calculating the second average value, the average value of all the

tactile sensing units

4, 5, 7, 8, 14 and 16 adjacent to the second average value can also be calculated; wherein the sensing signals of the un-triggered

tactile sensing units

14 and 16 can be regarded as zero. Therefore, the method better accords with the actual application scene based on the perfection of the area adjacent to the position of the maximum value of the collision force, improves the precision of collision detection, and reduces the probability of occurrence of misjudgment.

In some embodiments, the controller is configured with a first collision detection condition and a second collision detection condition, and when the sensing signal meets the first collision detection condition or the second collision detection condition, the mechanical arm can be judged to be in a collision state; when the sensing signal does not satisfy the first collision detection condition and does not satisfy the second collision detection condition, the mechanical arm is determined to be in a non-collision state, so that the collision state can be more accurately detected based on the sensing signal of the touch sensor, and the probability of the defects that the motion of the mechanical arm is invalid due to misjudgment of the collision state is reduced.

In some embodiments, when the first average value is greater than or equal to the first threshold δ ₁ When the first collision detection condition is met, determining that the mechanical arm is in a collision state; or, when the maximum value is greater than or equal to the second threshold value delta ₂ And the second average value is greater than or equal to a third threshold value delta ₃ When the second collision detection condition is met, determining that the mechanical arm is in a collision state; wherein the second threshold value delta ₂ Greater than a third threshold value delta ₃ 。

In some embodiments, the first threshold δ ₁ A second threshold value delta ₂ And a third threshold value delta ₃ The setting can be carried out according to the structure of the mechanical arm and the actual application scene, or a plurality of thresholds are configured in the controller and respectively correspond to different application scenes; in practical application, the threshold value can be switched according to different scenes so as to select different collision detection conditions. The first collision detection condition and the second collision detection condition may be selectively configured according to actual needs.

In some embodiments, based on the collision detection condition, the controller may further identify different collision states, and drive the mechanical arm to execute the obstacle avoidance motion mode based on the different collision states.

In some embodiments, the collision status comprises a first collision status or a second collision status; when the first average valuef is greater than or equal to a first threshold value delta ₁ And is less than or equal to a fourth threshold value delta ₄ When, or when the second average value f' is greater than or equal to the third threshold value delta ₃ And is less than or equal to a fourth threshold value delta ₄ And determining the collision state of the mechanical arm as a first collision state. When the first average value f is larger than the fourth threshold value delta ₄ When, or when, the second average value f' is greater than the fourth threshold value delta ₄ And determining the collision state of the mechanical arm as a second collision state. Wherein the fourth threshold value delta ₄ Greater than a first threshold value delta ₁ Fourth threshold value delta ₄ Greater than a third threshold value delta ₃ (ii) a Fourth threshold value δ ₄ The structure and the practical application scene of the mechanical arm can be set.

Based on the actual load capacity of the mechanical arm, the highest detection threshold value of the tactile sensor, namely the fourth threshold value delta, is set ₄ Based on the detected induction signal and the fourth threshold value delta ₄ The collision state of the mechanical arm is further more accurately determined. For example, when the mechanical arm contacts an obstacle in the current motion state, the sensing signal detected by the touch sensing unit of the triggered touch sensor may change constantly in real time with the motion state of the mechanical arm, so as to detect the collision state of the mechanical arm.

In some embodiments, the robot will take protective action immediately after detecting that the robotic arm is in a collision state to reduce collision injuries. Based on the collision detection condition triggering the collision state, selecting the corresponding collision force measurement indexes, and taking protective measures of different levels, namely different types of obstacle avoidance motion modes.

In some embodiments, the controller is configured with a collision avoidance function, the collision avoidance function comprising: and if the mechanical arm is in a motion state, driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state. Wherein, the collision state includes first collision state or second collision state, and the preset control mode includes at least one of following: a fallback control mode and an admittance control mode.

For example, when the mechanical arm touches during movement, collision detection of a collision state is triggeredUnder the condition of the first collision detection condition or the second collision detection condition, the first average value f is approximately used as the average value and the maximum value f of the collision force _max The approximation is the maximum value of the impact force, the second average value f' of the neighborhood is the approximation of the average value of the collision force of the neighborhood, and different levels of protective measures, such as a back-off control mode or an admittance control mode, are taken in different zones respectively.

In some embodiments, when the collision state is a first collision state, the mechanical arm is driven to move in an admittance control mode based on the induction signal; and when the collision state is a second collision state, driving the mechanical arm to move according to a backspacing control mode based on the induction signal.

In some embodiments, driving the robot arm in the admittance control mode based on the sensed signal comprises: and determining the running speed based on the induction signal, and driving the mechanical arm to continuously move at the running speed in the admittance control mode until the mechanical arm is not in the first collision state.

Illustratively, determining the operating speed based on the sense signal includes: reducing the running speed of the mechanical arm to a preset percentage D% of the original speed, wherein the preset percentage can be obtained by calculation based on a threshold interval where the induction signal is located, and the calculation formula is expressed as follows:

wherein the content of the first and second substances,

referring to fig. 6 (a), the original path of the robot arm is set from a first position a to a second position D; however, when the mechanical arm moves from the first position a to the third position B along the original path, and the mechanical arm is detected to be in the first collision state at the third position B, the admittance control mode of the mechanical arm is triggered, and at this time, the resultant force of the collision force applied to the mechanical arm is determined based on the sensing signal of the tactile sensing unit, and based on the resultant force, the operation speed is calculated by using the formula (3), and the mechanical arm moves to the fourth position C along the admittance control path at the operation speed, so that the mechanical arm is not in the first collision state; the admittance control path may be planned based on a resultant force direction of the collision force and a position of the collision area, and a specific planning algorithm of the admittance control path is not limited in this embodiment. When the robot arm moves in the admittance control mode, the attitude of the end of the robot arm may or may not change.

In some embodiments, driving the mechanical arm to move in a retraction control mode based on the sensing signal comprises: and based on the displacement direction determined by the induction signal, driving the mechanical arm to move by a preset step length along the displacement direction after the mechanical arm is controlled to stop.

Illustratively, when the mechanical arm is detected to be in the second collision state, the original speed of the mechanical arm is reduced to zero to control the mechanical arm to stop, and the mechanical arm is driven to move by a preset step length in the displacement direction determined based on the sensing signal. The preset step length may be a preset value, or may be determined and adjusted according to a real-time sensing signal, for example, the preset step length is determined according to the magnitude of the impact force represented by the sensing signal, and specifically, the preset step length may be positively correlated with the magnitude of the impact force. When the backspacing control mode is executed based on the induction signal, the posture of the mechanical arm can be controlled to be unchanged when the mechanical arm stops moving, and the mechanical arm moves in the displacement direction by a preset step length. The displacement direction may be determined based on the sensing signal of the triggered touch sensing unit, for example, a resultant force of collision forces of the mechanical arm is obtained based on the sensing signal, and the displacement direction of the retraction control is determined according to the magnitude and direction of the resultant force.

As shown in fig. 6 b, when the mechanical arm is detected to be in the second collision state when the mechanical arm moves to the position (1) along the original movement direction, the retraction control mode is triggered, and when the direction indicated by the arrow in the displacement pattern determined based on the sensing signal of the triggered tactile sensing unit is detected, the mechanical arm is controlled to stop moving and move in the determined displacement direction (when the mechanical arm moves to the position (2)). When a backspacing control mode is executed, the posture of the tail end of the mechanical arm can be kept unchanged, and the tail end of the mechanical arm is controlled in a linkage mode to realize the backspacing obstacle avoidance function by rotating each shaft of the mechanical arm. The direction of the resultant force F and the displacement direction of the retraction control shown in fig. 6 (b) are only schematically illustrated, and in a specific practical application scenario, the retraction and obstacle avoidance functions of the mechanical arm in any direction in space can be realized through the axis linkage control based on the direction of the resultant force.

In some embodiments, the controller is further configured with a touch teaching function, the touch teaching function including: and if the mechanical arm is in a static state, driving the mechanical arm to move in a preset teaching mode based on the induction signal.

For example, when the mechanical arm is in a static state and is touched by the outside, for example, a user touches the mechanical arm in the static state by flapping, pushing, pressing, or the like, the touch sensor may detect a sensing signal, and the controller determines a motion parameter, such as a motion direction and a motion speed, of the mechanical arm corresponding to the teaching mode based on the sensing signal, and drives the mechanical arm to move in the teaching mode based on the motion parameter.

For example, the preset teaching mode may include one or more of a position inching mode, a position linkage mode, a posture inching mode, a posture linkage mode or a position posture linkage mode.

When the teaching mode is the position inching mode, driving the mechanical arm to move in the teaching mode based on the motion parameter may include: determining a displacement direction based on an induction signal of a touch sensor, keeping the posture of the tail end of the mechanical arm unchanged, and driving the tail end of the mechanical arm to move a preset step length along the displacement direction determined in real time; when the teaching mode is the position linkage mode, driving the robot arm to move in the teaching mode based on the motion parameter may include: determining a displacement direction based on an induction signal of the touch sensor, keeping the posture of the tail end of the mechanical arm unchanged, and driving the tail end of the mechanical arm to continuously move along the displacement direction determined in real time until the induction signal of the touch sensor is smaller than a preset signal value; when the teaching mode is the gesture inching mode, driving the mechanical arm to move in the teaching mode based on the motion parameter may include: determining a rotation direction based on induction signals of the touch sensors in any two different areas, keeping the position of the tail end of the mechanical arm unchanged, and driving the tail end of the mechanical arm to rotate by a preset angle along the rotation direction determined in real time; when the teaching mode is the gesture linkage mode, driving the mechanical arm to move in the teaching mode based on the motion parameter may include: determining a rotation direction based on induction signals of the touch sensors in any two different areas, keeping the position of the tail end of the mechanical arm unchanged, and driving the tail end of the mechanical arm to continuously rotate along the rotation direction determined in real time until the induction signal of any touch sensor is smaller than a preset signal value; when the teaching mode is the position posture linkage mode, driving the mechanical arm to move in the teaching mode based on the motion parameters may include: the method comprises the steps of determining a displacement direction and a rotation direction based on induction signals of touch sensors in any two different areas, and driving the tail end of a mechanical arm to continuously move and rotate along the displacement direction and the rotation direction determined in real time until the induction signal of any touch sensor is smaller than a preset signal value.

Correspondingly, the controller can also switch the teaching mode of the mechanical arm based on the mode switching instruction. The embodiment realizes the teaching function through touching, has simplified the use of arm, and touch sensor has certain price advantage for six-dimensional force sensor, for traditional teaching method that drags based on six-dimensional force sensor, the manufacturing cost that this application scheme can reduce the arm to a certain extent improves the suitability of arm.

Another embodiment of the present application further provides a method for detecting a collision of a robot arm, as shown in fig. 7, the method for detecting a collision of a robot arm includes:

and S701, determining the collision state of the mechanical arm based on the sensing signal of the touch sensor.

In this embodiment, the sensing signal is used to represent force-receiving information in at least one direction, and the touch sensor may be disposed at the end of the mechanical arm; specifically, the manner of representing the force information by the sensing signal, the setting manner of the tactile sensor, and the process of determining the collision state may refer to the related descriptions in the foregoing embodiments, and details are not repeated herein.

And S702, if the mechanical arm is in a motion state, driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state.

In this embodiment, the robot will take protective action by the controller immediately after detecting the collision condition to reduce collision injuries. According to the collision detection condition triggering the collision state, selecting a corresponding collision force measurement index (a threshold index of the collision force corresponding to the collision state), and taking protective measures of different levels.

In some embodiments, the touch sensor includes a plurality of touch sensing units, each of which generates a corresponding sensing signal when a corresponding region is touched; determining a collision state of the robot arm based on a sensing signal of the tactile sensor, comprising: and determining the collision state of the mechanical arm based on the sensing signals of more than two touch sensing units in the collision area when the mechanical arm is touched.

In an application scenario, determining a collision state of a mechanical arm based on sensing signals of two or more tactile sensing units in a collision region when the mechanical arm is touched includes: and determining the collision state of the mechanical arm based on the first average value of the sensing signals of the more than two touch sensing units.

In another application scenario, determining a collision state of the mechanical arm based on sensing signals of two or more tactile sensing units in a collision region when the mechanical arm is touched includes: and determining the collision state of the mechanical arm based on the maximum value of the induction signals of more than two touch induction units and the second average value of the induction signals of the touch induction units adjacent to the touch induction unit corresponding to the maximum value.

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

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

Specifically, for the description of the calculation process and the representation of the first average value, the maximum value, and the second average value, reference may be made to the description in the foregoing embodiments, and details are not repeated herein.

In some embodiments, the collision state may include a first collision state or a second collision state; determining a collision state of the robot arm based on sensing signals of two or more tactile sensing units, which may further include: when the first average value is greater than or equal to a 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 a third threshold value and less than or equal to a fourth threshold value, determining that the collision state of the mechanical arm is the first collision state. And when the first average value is larger than a fourth threshold value, or when the second average value is larger than the fourth threshold value, determining that the collision state of the mechanical arm is a second collision state. Wherein the fourth threshold is greater than the first threshold, and the fourth threshold is greater than the third threshold.

In some embodiments, the preset control mode may include at least one of: a fallback control mode and an admittance control mode. Based on inductive signal and collision state according to predetermineeing control mode drive the arm motion includes: when the collision state is a first collision state, driving the mechanical arm to move according to an admittance control mode based on the induction signal; and when the collision state is a second collision state, driving the mechanical arm to move in a backspacing control mode based on the induction signal.

In one embodiment, the driving the mechanical arm to move in an admittance control mode based on the induction signal comprises: and determining the running speed based on the induction signal, and driving the mechanical arm to continuously move at the running speed in the admittance control mode until the mechanical arm is not in the first collision state.

In one embodiment, the driving of the mechanical arm in a retraction control mode based on the sensing signal comprises: and determining the displacement direction based on the induction signal, and driving the mechanical arm to move for a preset step length along the displacement direction after controlling the mechanical arm to stop.

It can be seen from above that, above-mentioned set up touch sensor in the arm to confirm the collision state of arm based on touch sensor's sensing signal, can be applicable to the collision detection of metal or non-metallic barrier, enlarge the range of application, and the sensing signal based on touch sensor carries out the detection of collision state, can improve the collision and detect the precision, be convenient for in time to the definite of collision state, thereby can reduce the probability of the impact injury that causes because the collision, make the arm more convenient and the cost is lower at practical application in-process.

And S703, if the mechanical arm is in a static state, driving the mechanical arm to move in a preset teaching mode based on the induction signal.

For example, when the mechanical arm is in a static state and is touched by the outside, the touch sensor may detect a sensing signal, and the controller determines, based on the sensing signal, a motion parameter, such as a motion direction and a motion speed, of the mechanical arm corresponding to the teaching mode, and drives the mechanical arm to move in the teaching mode based on the motion parameter.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not constitute any limitation to the implementation process of the embodiments of the present application.

By way of example, embodiments of the present application further provide a robot arm, including: the touch sensor, the memory and the processor are arranged on the mechanical arm, and the processor is used for reading and executing the computer program stored in the memory so as to realize the steps of the mechanical arm collision detection method. By way of example, the embodiment of the application also provides a robot comprising the mechanical arm.

Illustratively, the embodiment of the present application further provides a chip, which includes a processor, where the processor is configured to read and execute a computer program stored in a memory, so as to implement the steps of the above-described mechanical arm collision detection method.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the method solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. In addition, the integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.

The above examples are intended only to illustrate the system and method of the present application and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the method solutions described in the foregoing embodiments may be modified, or some of the method features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the method aspects of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A robot arm collision detection system, comprising:

a touch sensor arranged on the mechanical arm;

and a controller connected to the tactile sensor;

the controller is configured with a collision detection function including: and determining the collision state of the mechanical arm based on the sensing signals of the touch sensor, wherein the sensing signals are used for representing stress information in at least one direction.

2. The system of claim 1, wherein the tactile sensor comprises a plurality of tactile sensing elements, each tactile sensing element generating a respective sensing signal when a respective area is touched;

3. The system according to claim 2, wherein the determining the collision status of the robot arm based on the sensing signals of the two or more tactile sensing units within the collision zone when touched comprises:

4. The system of claim 3, wherein the controller is configured with a first collision detection condition and a second collision detection condition;

when the first average value is greater than or equal to a first threshold value, the first collision detection condition is met, and the mechanical arm is determined to be in the collision state; alternatively, the first and second electrodes may be,

5. The system of claim 4, wherein the collision status comprises a first collision status or a second collision status;

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

7. The system according to any one of claims 1 to 6, wherein the controller is configured with a collision avoidance function comprising: and if the mechanical arm is in a motion state, driving the mechanical arm to move according to a preset control mode based on the induction signal and the collision state.

8. The system of claim 7, wherein the collision status comprises a first collision status or a second collision status, and the preset control mode comprises at least one of: a fallback control mode and an admittance control mode;

9. The system of claim 8, wherein said driving the robotic arm in the admittance control mode based on the induced signal comprises:

10. The system according to any one of claims 1 to 6, wherein the controller is configured with a touch teaching function, the touch teaching function including: and if the mechanical arm is in a static state, driving the mechanical arm to move in a preset teaching mode based on the induction signal.

11. A mechanical arm collision detection method is characterized by comprising the following steps:

12. The method of claim 11, wherein the tactile sensor comprises a plurality of tactile sensing elements, each tactile sensing element generating a respective sensing signal when a respective area is touched;

13. The method of claim 12, wherein determining the collision status of the robotic arm based on the sensing signals of two or more tactile sensing units within the collision zone when touched comprises:

14. The method of claim 13, wherein determining the collision status of the robotic arm based on the sensing signals of the two or more tactile sensing units comprises:

15. The method of claim 14, wherein the collision status comprises a first collision status or a second collision status;

16. The method according to any one of claims 11 to 15, wherein after determining the collision status of the robot arm based on the sensing signal of the tactile sensor, the method further comprises:

17. The method of claim 16, wherein the collision status comprises a first collision status or a second collision status, and the preset control mode comprises at least one of: a fallback control mode and an admittance control mode;

18. The method of claim 17, wherein said driving the robotic arm in the admittance control mode based on the sensing signal comprises:

19. The method according to any one of claims 11 to 15, wherein after determining the collision status of the robot arm based on the sensing signal of the tactile sensor, the method further comprises:

20. A robot arm, comprising: a tactile sensor disposed on a robotic arm, a memory, and a processor for reading and executing a computer program stored in the memory to implement the steps of the method of any of claims 17-19.

21. A robot, comprising: a robotic arm as claimed in claim 20.

22. A chip comprising a processor for reading and executing a computer program stored in a memory to carry out the steps of the method according to any one of claims 11 to 19.