Guiding control method based on speed map and brain sense-like glove

Abstract

The invention discloses a guidance control method based on a speed map and a brain sense-like glove. The method comprises the following steps: constructing a hybrid vector field and a virtual potential field; combining the mixed vector field and the virtual potential field to construct a global convergence vector field as a velocity map; guidance coordinates are obtained, and a speed map is input to obtain guidance information; error information is obtained based on the guidance information and the current speed of the robot; and the method is substituted into a controller to realize robot control. According to the method, a global convergence vector is designed in advance to serve as a guide graph, the system state is guided to tend to be stable, so that the robot is attracted to an expected track when disturbance exists, the uncertainty and interference of the control system are compensated with the minimum calculated amount, and transient overshoot in the flexible interaction process is remarkably reduced; three-dimensional force is accurately estimated based on a brain sense-like glove, and flexible interaction of robots of any model and any number is realized in combination with a guide control method and an admittance relational expression.

Description

Technical Field

[0001] The present invention mainly relates to the field of robotics technology, and in particular to a guidance control method based on a speed map and a brain-like force perception glove. Background Art

[0002] In the field of robotics and human-computer interaction, how to achieve efficient, stable and flexible navigation and control of robots in complex environments has always been a hot topic and difficulty in research. Traditional robot control methods often rely on precise models and strict control conditions, but in practical applications, robots often face challenges such as environmental uncertainty, external interference and complex dynamic interactions, which often lead to decreased control performance and even system instability. Especially in situations where high-precision flexible interaction is required, such as medical surgical robots, precision manufacturing, and human-computer interaction equipment, extremely high requirements are placed on the control accuracy, response speed and stability of robots. However, most of the existing robot control technologies are based on classical control theory, which makes it difficult to effectively cope with complex and changeable interaction scenarios. Especially in flexible interaction processes that require fast response and high-precision control, traditional control methods often have problems such as unstable control effects and large transient overshoot.

[0003] In addition, with the continuous development of robotics technology, robots are no longer just tools for performing single tasks, but are increasingly involved in collaborative work with humans or other robots. In the process of human-computer interaction, due to the limitations of robot model, size and number, compliant interaction is difficult, and force sensors are expensive, making it difficult for each robot to be fully equipped. Therefore, developing an interactive device that can achieve high-precision flexible interaction between humans and multiple machines has become an urgent problem to be solved in the current field of human-computer interaction. Summary of the invention

[0004] The purpose of the present invention is to provide a guidance control method based on a velocity map and a brain-like force perception glove. The method aims to use a global convergence vector field as a guidance map to guide the robot to track the trajectory at any position and compensate for all disturbances of the robot system with the minimum control force. In the compliant interaction, the guidance control method effectively reduces the overshoot in the force contact process while compensating for the dynamic disturbance. Furthermore, in order to solve the problem of human and multi-machine interaction, a brain-like force perception glove is proposed to achieve coordinated work between humans and any number, model and size of robotic arms.

[0005] The technical solution of the present invention is as follows:

[0006] In one aspect, the present invention discloses a guidance control method based on a speed map, the method comprising the following steps:

[0007] S1. Construct a reasonable mixed vector field so that all points in the vector field can converge to the desired point;

[0008] S2, construct a suitable virtual potential field and combine it with the mixed vector field to achieve smooth convergence;

[0009] S3, combining the hybrid vector field and the virtual potential field to construct a global convergence vector field, so that all points in the map can smoothly converge to the target point, and use it as a velocity map;

[0010] S4, according to the predefined trajectory, obtain the guidance coordinates through the coordinate transformation equation, and input the speed map to obtain the guidance information in real time;

[0011] S5, obtaining an error based on the guidance information and the current speed of the robot;

[0012] S6. Substitute the error information into the controller to realize robot control.

[0013] Preferably, the global convergence vector field of step S3 is obtained by the hybrid vector field constructed in step S1 and the virtual potential field constructed in step S2, the hybrid vector field is constructed by superposition of multiple vector fields, the vector fields are all obtained based on predefined paths, the target path of the vector field is defined by the intersection of several hypersurfaces, each hypersurface is given by the zero level set of a smooth function; the global convergence vector field is expressed as:

[0014] In formula (1) is the global convergence vector field, i.e., the velocity map. n is the dimension of the vector field, s is the scale factor, n0 is the number of planes with zero in the vector field, S represents all axes in the n-dimensional space, and I represents the axis excluding x. w The axis set of the axis variable, X G is the vector field space, is each vector field in the mixed vector field; the X G It is expressed as:

[0015] X G =X = [x1, x2, ..., x n ] T (2)

[0016] In formula (2), X is the robot coordinate space; S and I are expressed as:

[0017] S=x k , k = 1, ..., n (3)

[0018] I=S\x w =i j , j = 1, ..., n-1 (4)

[0019] Among them, the error of the vector field is expressed as:

[0020]

[0021] In formula (5) yes The partial derivative vector of is expressed as:

[0022]

[0023] In formula (6) is a Kronecker function, expressed as:

[0024]

[0025] The mixed vector field is composed of n vector fields, and the expected paths of these vector fields can be expressed as

[0026]

[0027] In formula (8) is a path intersected by n-1 planes; the mixed vector field can be expressed as:

[0028]

[0029] In formula (9), sgn(·) is the sign function, r0 and k j are all normal numbers, ⊥ φ (X G ) is the outer product of all vectors, ⊥ φ (X G )=[v1,...,v n ] T , is a vector ⊥ φ (X G ) and all the elements in d w , is the virtual potential field constructed in step S2;

[0030] Preferably, the virtual potential field of step S2 is expressed as:

[0031]

[0032] In formula (10), e represents the natural logarithm.

[0033] Preferably, the mixed vector field of step S1 is expressed in two-dimensional space as:

[0034]

[0035] In formula (11), A is a [0 1; -1 0] matrix. is a vector The sum of all elements in .

[0036] Preferably, the coordinate transformation equation of step S4 is expressed as:

[0037] X g (t) = X(t) - X d (t) (12)

[0038] Where X g (t) is the position of the end effector after coordinate transformation, X(t) is the position of the robot in space, and X d (t) is the expected position; according to formula (1), the guidance information is expressed as

[0039] Preferably, the error in step S5 is expressed as

[0040]

[0041] In formula (13), k g is a positive constant, X g is the position of the robot in the global convergence vector field space coordinate system, X g =XX d , X d is the expected trajectory.

[0042] Preferably, the controller of step S6 is represented as:

[0043]

[0044] In formula (14), k c Is a normal number.

[0045] Preferably, the robot control in step S6 is to substitute the controller into the robot dynamics model for compliant trajectory tracking, and the robot dynamics model is a robot dynamics model, which is expressed as:

[0046]

[0047] In formula (15), M(q)∈R n×n represents the inertia matrix, represents the centripetal force and Coriolis force vector, G(q)∈R n represents the gravity matrix; vector q, and Represents the position, velocity and acceleration of the joint respectively; vector τ∈R n , τ e ∈Rn and τ d ∈R n Respectively represent the input torque, the external torque in the workspace and the unknown bounded disturbance; the M(q), G(q) consists of a nominal part and a bounded uncertain part, expressed as follows:

[0048]

[0049] The robot dynamics model can be expressed as:

[0050]

[0051] In formula (17), D(t) is

[0052] The τ is expressed as: τ = J (q) T u (18)

[0053] In formula (18), J(q) is the Jacobian matrix;

[0054] The τ e It can be expressed as: e =J(q) T F e (19)

[0055] In formula (19), F e For external forces;

[0056] The forward kinematics mapping between the end effector and the joint angle is X = L (q). The dynamic model of the robot arm can be expressed as:

[0057]

[0058] The robot control realizes compliant human-machine interaction through the admittance relationship, and the admittance relationship is expressed as:

[0059]

[0060] In formula (21), M d is the expected inertia, B d is the damping, K d is the stiffness matrix, X r , and is the reference trajectory position, velocity and acceleration; the reference trajectory is a shaped trajectory for compliant interaction; the coordinate transformation equation is expressed as:

[0061] X g (t) = x(t) - X r (t) (22)

[0062] The X g (t) is limited by a saturation function, expressed as

[0063]

[0064] In formula (23), K T is the threshold value, Representation vector Each element in is restricted to (-K T , K T );

[0065] The robot arm error E is expressed as

[0066]

[0067] Afterwards, equations (22) and (24) are substituted into equation (14) to obtain the controller u, and then u is substituted into the robot arm dynamics model equation (20) to achieve real-time control of the robot arm.

[0068] On the other hand, the present invention also discloses a brain-like force sensing glove, which adopts the guidance control method based on the speed map, and controls the robot in step S6 to substitute the controller into the robot dynamics model for smooth trajectory tracking; it includes a force estimation algorithm based on a brain-like neural network, an upper cover (1), an upper film (2), a piezoresistive material (3), a lower film (4) and a lower cover (5), a controller, and a main control console; the upper cover (1) is a glove-like structure fixedly connected to the side of the upper film (2), and the upper film (2) is provided with a wire for detecting The resistance value of the piezoresistive material (3) is measured. The piezoresistive material (3) can change its resistance value according to pressure. The piezoresistive material (3) is fixed to the upper film (2) and the lower film (4). The lower film (4) is provided with a wire for detecting the resistance value of the piezoresistive material (3). The lower film (4) is provided with a protrusion at each piezoresistive material position for increasing the detection range. The lower film (4) is fixedly connected to the lower sleeve surface (5). The lower sleeve surface (5) is fixedly connected to the side of the upper sleeve surface (1). The controller can collect the resistance change of the piezoresistive material (3) to obtain the pressure value.

[0069] Preferably, the controller comprises a brain-like chip, a micro single-chip computer and a wireless transmission module, wherein the brain-like chip is used to deploy the force estimation algorithm based on the brain-like neural network; the force estimation algorithm based on the brain-like neural network pre-collects a multi-channel pressure sequence output by multiple piezoresistive materials (3) of the brain-like force glove under different directions and forces, and uses a three-dimensional pressure sensor as a correct label during the collection process to construct a brain-like force glove data set; then, the collected force sequence is converted into a pulse sequence and input into a pulse neural network, and a brain-like three-dimensional force perception model is obtained by training, and three-dimensional force is obtained by inputting the force sequence of the brain-like force glove into the brain-like three-dimensional force perception model in real time; and the three-dimensional force signal is sent to the main control console through the wireless transmission module.

[0070] Preferably, during the human-machine interaction process, the master controller collects the three-dimensional force sense of the brain-like force sense gloves in real time, converts the force to the workspace of each robot to update the trajectory, and controls the robot through a guidance control method based on the speed map to achieve human-machine collaborative tasks.

[0071] The present invention provides a guidance control method based on a velocity map and a brain-like force perception glove, which have the following beneficial effects: by pre-designing a global convergence vector as a guidance map, the guidance system state tends to be stable, so that the robot is attracted to the desired trajectory in the presence of disturbances, and the uncertainty and interference of the control system are compensated with the minimum amount of calculation, and the transient overshoot in the flexible interaction process is significantly reduced. A brain-like neural network force perception glove is further designed to accurately estimate three-dimensional forces, combined with a guidance control method and an admittance relationship, so as to realize flexible interaction of any model and any number of robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0073] Figure 1 is a flow chart of a guidance control method based on a speed map according to the present invention;

[0074] Figure 2 is a schematic diagram of the structure of the brain-like force perception gloves of the present invention;

[0075] Figure 3 Schematic diagram of trajectory tracking errors of different controllers for D0 without disturbance; (a) GC tracking error; (b) ANIC tracking error; (c) SOBC tracking error; (d) external force;

[0076] Figure 4Schematic diagram of trajectory tracking error of time-varying disturbance D1; (a) GC tracking error; (b) ANIC tracking error; (c) SOBC tracking error; (d) GC actual trajectory;

[0077] Figure 5 Schematic diagram of the trajectory tracking error of the mixed disturbance D2; (a) GC tracking error; (b) ANIC tracking error; (c) SOBC tracking error; (d) GC actual trajectory;

[0078] Figure 6 Schematic diagram of trajectory tracking error of strong disturbance D3; (a) GC tracking error; (b) ANIC tracking error; (c) SOBC tracking error; (d) GC vector field error;

[0079] Figure 7 is the tracking error of the PD controller under different disturbances; (a) D0; (b) D1; (c) D2; (d) D3.

[0080] Description of reference numerals:

[0081] An upper sleeve surface (1), an upper film (2), a piezoresistive material (3), a lower film (4) and a lower sleeve surface (5). Root mean square error (RMS), root mean square error of the x-axis (zx), root mean square error of the y-axis (zy) and root mean square error of the z-axis (zz), a reference trajectory (Xr), a position of the end effector of the manipulator (X), a controller (GC) of the present invention, an adaptive neural network controller (ANIC), a controller based on a state observer (SOBC), a PD controller (PDC), no disturbance (D0), a time-varying disturbance (D1), a mixed disturbance (D2), and a strong disturbance (D3). DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0084] like Figure 1 This embodiment provides a guidance control method based on a speed map, the method comprising the following steps:

[0085] S1. Construct a reasonable mixed vector field so that all points in the vector field can converge to the desired point;

[0086] S2, construct a suitable virtual potential field and combine it with the mixed vector field to achieve smooth convergence;

[0087] S3, combining the hybrid vector field and the virtual potential field to construct a global convergence vector field, so that all points in the map can smoothly converge to the target point, and use it as a velocity map;

[0088] S4, according to the predefined trajectory, obtain the guidance coordinates through the coordinate transformation equation, and input the speed map to obtain the guidance information in real time;

[0089] S5, obtaining an error based on the guidance information and the current speed of the robot;

[0090] S6. Substitute the error information into the controller to realize robot control.

[0091] Furthermore, the global convergence vector field of step S3 is obtained by the hybrid vector field constructed in step S1 and the virtual potential field constructed in step S2, the hybrid vector field is constructed by superposition of multiple vector fields, the vector fields are all obtained based on predefined paths, the target path of the vector field is defined by the intersection of several hypersurfaces, each hypersurface is given by the zero level set of a smooth function; the global convergence vector field is expressed as:

[0092]

[0093] In formula (1) is the global convergence vector field, i.e., the velocity map. n is the dimension of the vector field, s is the scale factor, n0 is the number of planes with zero in the vector field, S represents all axes in the n-dimensional space, and I represents the axis excluding x. w The axis set of the axis variable, X G is the vector field space, is each vector field in the mixed vector field; the X G It is expressed as:

[0094] X G =X = [x1, x2, ..., x n ] T (2)

[0095] In formula (2), X is the robot coordinate space; S and I are expressed as:

[0096] S=x k , k = 1, ..., n (3)

[0097] I=S\x w =i j , j = 1, ..., n-1 (4)

[0098] Among them, the error of the vector field is expressed as:

[0099]

[0100] In formula (5) yes The partial derivative vector of is expressed as:

[0101]

[0102] In formula (6) is a Kronecker function, expressed as:

[0103]

[0104] The mixed vector field is composed of n vector fields, and the expected paths of these vector fields can be expressed as

[0105]

[0106] In formula (8) is a path intersected by n-1 planes; the mixed vector field can be expressed as:

[0107]

[0108] In formula (9), sgn(·) is the sign function, r0 and k j are all normal numbers, ⊥ φ (X G ) is the outer product of all vectors, ⊥ φ (X G )=[v1,...,v n ] T , is a vector ⊥ φ (X G ) and all the elements in d w The virtual potential field constructed in step S2.

[0109] Furthermore, the virtual potential field of step S2 is expressed as:

[0110]

[0111] In formula (10), e represents the natural logarithm.

[0112] Furthermore, the mixed vector field of step S1 is expressed in two-dimensional space as:

[0113]

[0114] In formula (11), A is a [0 1; -1 0] matrix. is a vector The sum of all elements in .

[0115] Furthermore, the coordinate transformation equation of step S4 is expressed as:

[0116] X g (t) = X(t) - X d (t) (12)

[0117] Where X g (t) is the position of the end effector after coordinate transformation, X(t) is the position of the robot in space, and X d (t) is the expected position; according to formula (1), the guidance information is expressed as

[0118] Furthermore, the error of step S5 is expressed as

[0119]

[0120] In formula (13), k g is a positive constant, X g is the position of the robot in the global convergence vector field space coordinate system, X g =XX d , X d is the expected trajectory.

[0121] Further, the controller of step S6 is expressed as:

[0122]

[0123] In formula (14), k c Is a normal number.

[0124] Furthermore, the robot control in step S6 is to substitute the controller into the robot dynamics model for compliant trajectory tracking, and the robot dynamics model is a robot dynamics model, which is expressed as:

[0125]

[0126] In formula (15), M(q)∈R n×n represents the inertia matrix, represents the centripetal force and Coriolis force vector, G(q)∈R n represents the gravity matrix; vector q, and Represents the position, velocity and acceleration of the joint respectively; vector τ∈R n , τ e ∈R n and τ d∈R n Respectively represent the input torque, the external torque in the workspace and the unknown bounded disturbance; the M(q), G(q) consists of a nominal part and a bounded uncertain part, expressed as follows:

[0127]

[0128] The robot dynamics model can be expressed as:

[0129]

[0130] In formula (17), D(t) is

[0131] The τ is expressed as: τ = J (q) T u (18)

[0132] In formula (18), J(q) is the Jacobian matrix;

[0133] The τ e It can be expressed as: e =J(q) T F e (19)

[0134] In formula (19), F e For external forces;

[0135] The forward kinematics mapping between the end effector and the joint angle is X = L (q). The dynamic model of the robot arm can be expressed as:

[0136]

[0137] The robot control realizes compliant human-machine interaction through the admittance relationship, and the admittance relationship is expressed as:

[0138]

[0139] In formula (21), M d is the expected inertia, B d is the damping, K d is the stiffness matrix, X r , and is the reference trajectory position, velocity and acceleration; the reference trajectory is a shaped trajectory for compliant interaction; the coordinate transformation equation is expressed as:

[0140] X g (t) = X(t) - X r (t) (22)

[0141] The Xg (t) is limited by a saturation function, expressed as

[0142]

[0143] In formula (23), K T is the threshold value, Representation vector Each element in is restricted to (-K T , K T );

[0144] The robot arm error E is expressed as

[0145]

[0146] Afterwards, equations (22) and (24) are substituted into equation (14) to obtain the controller u, and then u is substituted into the robot arm dynamics model equation (20) to achieve real-time control of the robot arm.

[0147] like Figure 3 As shown, a brain-like force-sensing glove comprises a force estimation algorithm based on a brain-like neural network, an upper cover (1), an upper film (2), a piezoresistive material (3), a lower film (4) and a lower cover (5), a controller and a main control console; the upper cover (1) is a glove-like structure fixedly connected to the side of the upper film (2), the upper film (2) is provided with a wire for detecting the resistance value of the piezoresistive material (3), the piezoresistive material (3) can change its resistance value according to pressure, the piezoresistive material (3) is fixed to the upper film (2) and the lower film (4), the lower film (4) is provided with a wire for detecting the resistance value of the piezoresistive material (3), and the lower film (4) is provided with a protrusion at each piezoresistive material position for increasing the detection range; the lower film (4) is fixedly connected to the lower cover (5), and the lower cover (5) is fixedly connected to the side of the upper cover (1); the controller can collect the resistance change of the piezoresistive material (3) to obtain the pressure value. The robot control of step S6 is to substitute the controller into the robot dynamics model for compliant trajectory tracking.

[0148] Select a dynamic model of a robotic arm for simulation comparison. The dynamic model is expressed as:

[0149]

[0150] in,

[0151] A=sin(q_1)sin(q_2)+cos(q_1)cos(q_2)$, $B

[0152] =cos(q_1)sin(q_2)-sin(q_1)cos(q2)

[0153] g=9.8kg / N

[0154] The length of each connecting rod is 1m, and the mass of the first and second connecting rods is 5kg and 10kg respectively. Comparative experiments were conducted using PDC, SOBC and ANIC. The proposed GC parameters are k c =4000, k g =400, s=1 / 3, q1=q2=1 / 2rad, r o =1, k j =1, K T =0.5 and j=1,2.

[0155] Furthermore, the controller includes a brain-like chip, a micro single-chip computer and a wireless transmission module, wherein the brain-like chip is used to deploy the force estimation algorithm based on the brain-like neural network; the force estimation algorithm based on the brain-like neural network collects the output multi-channel pressure sense sequences of multiple piezoresistive materials (3) of the brain-like force sense glove in different directions and forces in advance, and uses the three-dimensional pressure sensor as the correct label during the collection process to construct a brain-like force sense glove data set; then, the collected force sense sequence is converted into a pulse sequence and input into the pulse neural network, and a brain-like three-dimensional force sense perception model is obtained by training, and the three-dimensional force is obtained by inputting the force sense sequence of the brain-like force sense glove into the brain-like three-dimensional force sense perception model in real time; and the three-dimensional force signal is sent to the main control console through the wireless transmission module. During the human-machine interaction process, the main controller collects the three-dimensional force sense of the brain-like force sense glove in real time, and converts the force into the workspace of each robot for trajectory update, and controls the robot through a guidance control method based on a speed map to achieve human-machine collaborative tasks.

[0156] This example verifies the performance of GC through four sets of experiments. The expected trajectory of the end effector is The parameter of the admittance relation is M d =diag([1,1]),B d =diag([40,40]) and K d =diag([300,800]), during the time 5-7s, the external force is F e =[20sin(t),20sin(t)] T , the disturbance is D0 = [0, 0] T , D1=[(t)+400(t), 600(t)+200(t)] T , and

[0157] Figure 3The performance of different controllers in a non-interference environment is shown. GC, PDC, ANIC and SOBC have strong trajectory tracking performance, among which PDC has the best tracking ability.

[0158] Figure 4 and 5 represents the tracking performance of various controllers under time-varying and mixed disturbances. It can be seen that due to the influence of disturbances, the tracking performance of ANIC and SOBC is significantly reduced, among which ANIC has better anti-disturbance than SOBC, while SOBC and ANIC still have considerable overshoot in the absence of external force. When contact force exists, the mixed disturbance aggravates the overshoot of ANIC. It is worth noting that the performance of GC is not affected by disturbances, maintains low computational complexity and high tracking accuracy, and effectively suppresses the overshoot caused by contact force.

[0159] However, if Figure 7 As shown in Figure 2, the trajectory tracking error of PDC under various interferences is large, indicating that its anti-interference ability is insufficient. Figure 6 As shown, when the external force F e Both ANIC and SOBC have considerable overshoot during interaction and disengagement, while GC effectively suppresses the overshoot, resulting in smoother trajectory tracking. Tables 1 and 2 further emphasize that GC achieves high-precision control with minimal control in a disturbance environment. Table 1 shows the root mean square error of different controllers. Table 2 shows the running time of different controllers with 2000 iterations.

[0160] Table 1

[0161]

[0162] Table 2

[0163]

[0164] Although strong interferences are rare, they may occur in actual control processes due to equipment failure or other factors. Figure 7 The performance of different controllers under such severe disturbances is illustrated. Under strong disturbances, neither SOBC nor ANIC can effectively track the trajectory. Therefore, GC can also maintain high control accuracy under strong disturbances.

[0165] In all experiments, the proposed guidance control method based on a velocity map has the shortest response time, while the neural network-based controller has the longest response time, and the guidance control scheme effectively compensates for all uncertainties and disturbances with minimal computational effort.

[0166] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description, and do not indicate or imply that the referred device or element must have a specific direction, be constructed and operate in a specific direction. Therefore, it should not be understood as a limitation of the present invention.

Claims

1. A guidance control method based on a speed map, characterized in that: The method comprises the following steps: S1. Construct a mixed vector field, in which all points can converge to the desired point; S2, constructing a virtual potential field, and combining the mixed vector field to achieve smooth convergence; S3, combining the hybrid vector field and the virtual potential field to construct a global convergence vector field so that all points in the map can smoothly converge to the target point, and using the global convergence vector field as a speed map; S4. According to the predefined trajectory, obtain the guidance coordinates through the coordinate transformation equation, and input the guidance coordinates into the speed map to obtain the guidance information in real time; S5. Obtaining error information based on the guidance information and the current speed of the robot; S6. Realize robot control by substituting the error information into the controller.

2. The guidance control method based on the speed map according to claim 1, characterized in that: The global convergence vector field of step S3 is obtained by the hybrid vector field constructed in step S1 and the virtual potential field constructed in step S2. The hybrid vector field is constructed by superposition of multiple vector fields. The multiple vector fields are all obtained based on predefined paths. The target paths of the multiple vector fields are defined by the intersection of several hypersurfaces, and each hypersurface is given by the zero level set of a smooth function. The global convergence vector field is expressed as: In formula (1) is the global convergence vector field, i.e., the velocity map. n is the dimension of the vector field, s is the scale factor, n0 is the number of planes with 0 in the vector field, S represents all axes in the n-dimensional space, I represents the axis set excluding the xw axis variables, and X G is the vector field space, is each vector field in the mixed vector field; the X G It is expressed as: X G =X=[x1,x2,...,x n ] T (2) In formula (2), X is the robot coordinate space; S and I are expressed as: S=x k ,k=1,...,n (3) I=S\x w =i j ,j=1,...,n-1 (4) Among them, the error of the vector field is expressed as: In formula (5) 3. The guidance control method based on the speed map according to claim 2, characterized in that: The mixed vector field of step S1 can be expressed as: In formula (9), sgn(·) is the sign function, r0 and k j are all normal numbers, ⊥ φ (X G )=[v1,…,v n ] T , is a vector ⊥ φ (X G ), yes The partial derivative vector of w The virtual potential field constructed in step S2; the virtual potential field is expressed as: In formula (10), e represents the natural logarithm.

4. The guidance control method based on the speed map according to claim 3 is characterized in that: The coordinate transformation equation of step S4 is expressed as: X g (t)=X(t)-X d (t) (12) Where X g (t) is the position of the end effector after coordinate transformation, X(t) is the position of the robot in space, and X d (t) is the expected position.

5. The guidance control method based on the speed map according to claim 4 is characterized in that: The error of step S5 is expressed as: In formula (13), k g Is a normal number.

6. The guidance control method based on the speed map according to claim 5, characterized in that: The controller of step S6 is represented as: In formula (14), k c Is a normal number.

7. The guidance control method based on speed map according to claim 6, characterized in that: The robot control in step S6 is to substitute the controller into the robot dynamics model for compliant trajectory tracking, and the robot dynamics model is a robot dynamics model, which is expressed as: In formula (15), M(q)∈R n×n represents the inertia matrix, represents the centripetal force and Coriolis force vector, G(q)∈R n represents the gravity matrix; Vector q, and Represents the position, velocity and acceleration of the joint respectively; vector τ∈R n , τ e ∈R n and τ d ∈R n Respectively represent the input torque, the external torque in the workspace and the unknown bounded disturbance; the M(q), G(q) consists of a nominal part and a bounded uncertain part, expressed as follows: The robot dynamics model can be expressed as: In formula (17), D(t) is The forward kinematics mapping between the end effector and the joint angle is X = L (q); the dynamic model of the robot arm can be expressed as: The coordinate transformation equation is expressed as: X g (t)=X(t)-X r (t) (22) The robot arm error E is expressed as: Afterwards, equations (22) and (24) are substituted into equation (14) to obtain the controller u, and then u is substituted into the robot arm dynamics model equation (20) to achieve real-time control of the robot arm.

8. A brain-like perception glove, characterized in that: Adopting a guidance control method based on a velocity map as described in any one of claims 1 to 7, substituting the controller into a robot dynamics model for compliant trajectory tracking; The invention comprises a force estimation algorithm based on a brain-like neural network, an upper cover (1), an upper film (2), a piezoresistive material (3), a lower film (4) and a lower cover (5), a controller and a main control console; the upper cover (1) is a glove-like structure fixedly connected to the side of the upper film (2); the upper film (2) is provided with a wire for detecting the resistance value of the piezoresistive material (3); the piezoresistive material (3) can change its resistance value according to pressure; the piezoresistive material (3) is fixed to the upper film (2) and the lower film (4); the lower film (4) is provided with a wire for detecting the resistance value of the piezoresistive material (3); the lower film (4) is provided with a protrusion at each piezoresistive material position for increasing the detection range; the lower film (4) is fixedly connected to the lower cover (5); the lower cover (5) is fixedly connected to the side of the upper cover (1); the controller can collect the resistance change of the piezoresistive material (3) to obtain the pressure value.

9. The brain-like perception glove according to claim 8, characterized in that: The controller comprises a brain-like chip, a micro single-chip computer and a wireless transmission module, wherein the brain-like chip is used to deploy the force estimation algorithm based on the brain-like neural network; the force estimation algorithm based on the brain-like neural network pre-collects a multi-channel pressure sense sequence output by a plurality of piezoresistive materials (3) of the brain-like force sense glove under different directions and forces, and uses a three-dimensional pressure sensor as a correct label during the collection process to construct a brain-like force sense glove data set; then, the collected force sense sequence is converted into a pulse sequence and input into a pulse neural network, and a brain-like three-dimensional force sense perception model is obtained by training, and three-dimensional force is obtained by inputting the force sense sequence of the brain-like force sense glove into the brain-like three-dimensional force sense perception model in real time; And the three-dimensional force signal is sent to the main control console through the wireless transmission module.

10. The brain-like perception glove according to claim 9, characterized in that: During the human-machine interaction process, the master controller collects the three-dimensional force perception of the brain-like force perception gloves in real time, converts the force to the workspace of each robot to update the trajectory, and controls the robot through a guidance control method based on the speed map to achieve human-machine collaborative tasks.

Images