Multi-degree-of-freedom robot operating system

Abstract

The invention discloses a multi-degree-of-freedom robot operating system, and belongs to the technical field of robots. Comprising a plurality of sensors, a sensor fusion module, a path planning module, a position control module and a speed adjusting module, wherein the sensor fusion module is used for fusing information acquired by the plurality of sensors; the path planning module adopts a path planning model based on artificial intelligence to plan a motion path and outputs an instruction; the speed adjusting module adjusts the speed of the robot based on the instruction; and the position control module adjusts the rotation angle of the robot based on the instruction. The robot motion consistency and stability can be guaranteed, and the task completion quality is improved. Therefore, user requirements can be better met and more efficient and personalized service experience can be provided.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and more particularly to a multi-degree-of-freedom robot operating system. Background Art

[0002] Artificial intelligence technology has made significant progress in recent years, but its application in robot operating systems is still not deep enough, especially in path planning. Many systems still use relatively basic methods to determine the movement route and fail to fully utilize the potential brought by AI.

[0003] At the same time, traditional path planning algorithms often rely on pre-set rules or simple heuristic methods, which are rigid and difficult to adjust quickly when faced with complex dynamic environments, and cannot cope well with real-time changes.

[0004] Therefore, how to provide a multi-degree-of-freedom robot operating system is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, the present invention provides a multi-degree-of-freedom robot operating system to solve the technical problems existing in the above-mentioned prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A multi-degree-of-freedom robot operating system, comprising:

[0008] Multiple sensors, sensor fusion module, path planning module, position control module and speed regulation module;

[0009] in,

[0010] The sensor fusion module fuses the information acquired by the multiple sensors;

[0011] The path planning module plans the motion path using an artificial intelligence-based path planning model and outputs instructions;

[0012] The speed adjustment module adjusts the speed of the robot based on the instruction;

[0013] The position control module adjusts the rotation angle of the robot based on the instruction.

[0014] Furthermore, the sensor includes: a position sensor and a visual sensor.

[0015] Furthermore, the sensor fusion module uses an extended Kalman filter to fuse the data of the visual sensor and the position sensor.

[0016] Furthermore, the path planning module includes:

[0017] Initialize the unit, define the target point, and determine the obstacle position based on the fused vision sensor and position sensor data;

[0018] A total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit;

[0019] A control force calculation unit, which determines the control force by a gradient descent method based on the total potential field;

[0020] A control law calculation unit uses control forces to adjust the robot's linear and angular velocities;

[0021] The update unit uses a nonlinear dynamic model to describe the robot's motion and updates the robot's position at the next time step based on the calculated linear and angular velocities.

[0022] Furthermore, the total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit, including:

[0023] Compute the attractive potential field:

[0024]

[0025] In the formula, k att is the proportionality coefficient of the attractive potential field; E n is the vector from the current position to the target point;

[0026] Compute the repulsive potential field:

[0027]

[0028] In the formula, k rep is the proportionality coefficient of the repulsive potential field; d 1 is the distance between the robot and the obstacle; d 0 is the emergency stopping distance;

[0029] Total potential field:

[0030] U(x,y)=U att (x,y)+Ur ep (x,y);

[0031] Where U(x,y) is the total potential field.

[0032] The control force calculation unit determines the control force based on the total potential field by gradient descent method, including:

[0033] F(x,y)=-▽U(x,y);

[0034] in:

[0035]

[0036] Where U(x,y) is the total potential field, F(x,y)=(F x ,F y ) is the control force.

[0037] Furthermore, the control law calculation unit uses the control force to adjust the linear velocity and angular velocity of the robot, where:

[0038] Line speed:

[0039]

[0040] Line Angle:

[0041] ω=arctan2(F y ,F x )-θ

[0042] In the formula, F x ,F y is the control force; θ is the direction angle corresponding to the robot.

[0043] Furthermore, the total potential field calculation unit uses a nonlinear dynamics model and a Q-learning algorithm to update the position of the robot at the next time step.

[0044] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a multi-degree-of-freedom robot operating system, and the path planning based on artificial intelligence enables the robot to flexibly avoid obstacles in complex environments and find the best route, while reducing unnecessary energy consumption and time costs, ensuring the consistency and stability of the robot's movements, and improving the quality of task completion. It can better meet user needs and provide a more efficient and personalized service experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0046] Figure 1 The figure is a schematic diagram of the structure of a multi-degree-of-freedom robot operating system of the present invention. DETAILED DESCRIPTION

[0047] 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.

[0048] See also Figure 1 , an embodiment of the present invention discloses a multi-degree-of-freedom robot operating system, comprising:

[0049] Multiple sensors, sensor fusion module, path planning module, position control module and speed regulation module;

[0050] in,

[0051] The sensor fusion module fuses the information acquired by the multiple sensors;

[0052] The path planning module plans the motion path using an artificial intelligence-based path planning model and outputs instructions;

[0053] The speed adjustment module adjusts the speed of the robot based on the instruction;

[0054] The position control module adjusts the rotation angle of the robot based on the instruction.

[0055] In a specific embodiment, the sensor includes: a position sensor and a visual sensor.

[0056] In a specific embodiment, the sensor fusion module uses an extended Kalman filter to fuse data from a visual sensor and a position sensor, including:

[0057] Construct the state equation of EKF;

[0058] x k =f(x k-1 ,u k )+w k ;

[0059] In the formula, x k It is a state vector, which contains the fused feature information (position, shape, color information) of the target object at time step k.

[0060] Observation equation:

[0061] z k =h(x k )+v k ;

[0062] In the formula, z kis the observation vector, containing the measurement data from different sensors. h is a nonlinear function that maps the state to the observation space. k is the observation noise, which is also assumed to be Gaussian white noise.

[0063] In a specific embodiment, the path planning module includes:

[0064] Initialize the unit, define the target point, and determine the obstacle position based on the fused vision sensor and position sensor data;

[0065] A total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit;

[0066] A control force calculation unit, which determines the control force by a gradient descent method based on the total potential field;

[0067] A control law calculation unit uses control forces to adjust the robot's linear and angular velocities;

[0068] The update unit uses a nonlinear dynamic model to describe the robot's motion and updates the robot's position at the next time step based on the calculated linear and angular velocities.

[0069] In a specific embodiment, the total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit, including:

[0070] Compute the attractive potential field:

[0071]

[0072] In the formula, k att is the proportionality coefficient of the attractive potential field; E n is the vector from the current position to the target point;

[0073] Compute the repulsive potential field:

[0074]

[0075] In the formula, k rep is the proportionality coefficient of the repulsive potential field; d 1 is the distance between the robot and the obstacle; d 0 is the emergency stopping distance;

[0076] Total potential field:

[0077] U(x,y)=U att (x,y)+Ur ep (x,y);

[0078] Where U(x,y) is the total potential field, which is the sum of the attractive potential field and the repulsive potential field.

[0079] The control force calculation unit determines the control force based on the total potential field by gradient descent method, including:

[0080] F(x,y)=-▽U(x,y);

[0081] in:

[0082]

[0083] Where U(x,y) is the total potential field, F(x,y)=(F x ,F y ) is the control force.

[0084] In a specific embodiment, the control law calculation unit uses the control force to adjust the linear velocity and angular velocity of the robot, wherein:

[0085] Line speed:

[0086]

[0087] Line Angle:

[0088] ω=arctan2(F y ,F x )-θ

[0089] In the formula, F x ,F y is the control force; θ is the direction angle corresponding to the robot.

[0090] In a specific embodiment, the total potential field calculation unit uses a nonlinear dynamics model and a Q-learning algorithm to update the position of the robot at the next time step.

[0091] In a specific embodiment, the current state of the multi-degree-of-freedom robot consists of a position and an orientation angle, that is, s = (x, y, θ), and the action is a = (v, ω).

[0092] Specifically, the nonlinear dynamic model is:

[0093] x′(t+1)=x(t)+v(t)cos(θ(t))Δt

[0094] y′(t+1)=y(t)+v(t)sin(θ(t))Δt;

[0095] θ′(t+1)=θ(t)+ω(t)Δt

[0096] Where v(t) is the current linear velocity of the robot, ω(t) is the current angular velocity of the robot, θ is the direction angle corresponding to the robot, x', y' is the motion position, θ' is the motion direction angle, and Δt is the time step.

[0097] In a specific embodiment, the immediate reward r is calculated according to the new state s′;

[0098] Specifically, the reward function is defined according to the task requirements, such as approaching the target point, avoiding obstacles, etc.

[0099] Update the Q value according to the Q-learning formula:

[0100] Q(s,a)←Q(s,a)+α[r+γmax a′ Q(s′,a′)-Q(s,a)]

[0101] In a specific embodiment, the current state s=(x 0 ,y 0 ,θ 0 ), action a=(v 0 ,ω 0 ), time step Δt = 0.1, the second reward function r is calculated based on the distance from the target point and whether it collides with an obstacle, then:

[0102] (x 0 ,y 0 ,θ 0 ),(v 0 ,ω 0 ))←Q((x 0 ,y 0 ,θ 0 ),(v 0 ,ω 0 ))+α[r+γmax a′ Q((x′,y′,θ′),a′)-Q((x 0 ,y 0 ,θ 0 ),(v 0 ,ω 0 ))]

[0103] Through the above solution, more accurate path planning and control can be achieved.

[0104] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0105] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-degree-of-freedom robot operating system, characterized in that: include: Multiple sensors, sensor fusion module, path planning module, position control module and speed regulation module; in, The sensor fusion module fuses the information acquired by the multiple sensors; The path planning module plans the motion path using an artificial intelligence-based path planning model and outputs instructions; The speed adjustment module adjusts the speed of the robot based on the instruction; The position control module adjusts the rotation angle of the robot based on the instruction.

2. A multi-degree-of-freedom robot operating system according to claim 1, characterized in that: The sensors include: a position sensor and a visual sensor.

3. A multi-degree-of-freedom robot operating system according to claim 2, characterized in that: The sensor fusion module uses an extended Kalman filter to fuse the data from the vision sensor and the position sensor.

4. A multi-degree-of-freedom robot operating system according to claim 1, characterized in that: The path planning module comprises: Initialize the unit, define the target point, and determine the obstacle position based on the fused vision sensor and position sensor data; A total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit; A control force calculation unit, which determines the control force by a gradient descent method based on the total potential field; A control law calculation unit uses control forces to adjust the robot's linear and angular velocities; The update unit updates the position of the robot at the next time step based on the calculated linear velocity and angular velocity.

5. A multi-degree-of-freedom robot operating system according to claim 4, characterized in that: The total potential field calculation unit calculates the total potential field according to the parameters of the initialization unit, including: Compute the attractive potential field: In the formula, k att is the proportionality coefficient of the attractive potential field; E n is the vector from the current position to the target point; Compute the repulsive potential field: In the formula, k rep is the proportional coefficient of the repulsive potential field; d1 is the distance between the robot and the obstacle; d0 is the emergency stop distance; Total potential field: U(x,y)=U att (x,y)+Ur ep (x,y); Where U(x,y) is the total potential field.

6. A multi-degree-of-freedom robot operating system according to claim 4, characterized in that: The control force calculation unit determines the control force based on the total potential field by gradient descent method, including: F(x,y)=-▽U(x,y); in: Where U(x,y) is the total potential field, F(x,y)=(F x ,F y ) is the control force.

7. A multi-degree-of-freedom robot operating system according to claim 4, characterized in that: The control law calculation unit uses the control force to adjust the robot's linear velocity and angular velocity, where: Line speed: Line Angle: ω=arctan2(F y ,F x )-θ In the formula, F x ,F y is the control force; θ is the corresponding direction angle of the robot.

8. The multi-degree-of-freedom robot operating system according to claim 4, characterized in that: The total potential field calculation unit uses a nonlinear dynamics model and a Q-learning algorithm to update the position of the robot at the next time step.

Images