Method and system for autonomously controlling ship through mechanical arm
Through the communication and interaction between the robotic arm and the console, the ship's action information is defined based on environmental and attitude data, the action instructions are matched and the joint trajectory is regulated, which solves the problem that traditional ships cannot achieve unmanned control and realizes the ship's autonomous control and stability .
Patent Information
- Application Number
- CN202410991138.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
The existing unmanned ship control technology cannot achieve independent control of traditional ships, especially because its actuator uses hydraulic or soft shaft transmission, which cannot achieve real-time environmental perception and action control.
Through the communication and interaction between the robotic arm and the console, the ship's action information is defined based on the surrounding environment and posture data, the robotic arm's action instructions are matched, the action path is planned and the joint activity trajectory is regulated, the steering wheel and throttle data are collected, and the throttle and directional robotic arm workload is defined. , realize independent control of the ship.
It realizes the control of the console by the robot arm, realizes the unmanned control of the ship, ensures the independent control of the ship and the stability of the water, and has sufficient practical value.
Smart Images

Figure CN118927241A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of autonomous control systems of a robot arm for a ship, and in particular to a method and system for autonomous control of a robot arm for a ship. Background Art
[0002] With the development of science and technology, and the development of unmanned technology, the unmanned operation of ships has also made significant progress. The current unmanned control usually requires the ship's actuator to have a wire control function, that is, to control it through the bus communication protocol. However, most of the existing traditional ships, such as fishing boats, cargo ships, cruise ships, speedboats, commercial ships, etc., all use hydraulic, flexible shaft and other transmission methods to control the actuator, and cannot achieve unmanned control of the ship. Summary of the invention
[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a method and system for autonomous control of a ship by a robotic arm. When the robotic arm and a control console are in a communication and interaction state, the motion information of the ship is defined based on the detection of the surrounding environment data and posture data; the motion instructions of the robotic arm are matched according to the motion information of the ship; in the motion instructions of the robotic arm, the motion path of the robotic arm is defined based on the motion instructions; the activity trajectories of multiple joints in the robotic arm are regulated based on the motion path, and time series actions and real-time obstacle avoidance control are planned; the rotation angle of the steering wheel and the throttle amount in the ship are collected, and the throttle robotic arm workload and the steering robotic arm workload are defined according to the rotation angle of the steering wheel and the throttle amount in the ship; the motion paths of the corresponding joints are defined according to the throttle robotic arm workload and the steering robotic arm workload, so as to complete the autonomous control of the ship, thereby realizing the control and control of the control console by the robotic arm and realizing unmanned control of the ship, which has sufficient practical value.
[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for autonomously controlling a ship by a robotic arm, which is applied to unmanned control scenarios of ships;
[0005] The method for autonomously controlling a ship by the mechanical arm comprises:
[0006] When the manipulator and the control console are in a communication interaction state, based on detecting the surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data;
[0007] Match the action instructions of the robotic arm according to the action information of the ship;
[0008] In the motion instruction of the robot arm, a motion path of the robot arm is defined based on the motion instruction;
[0009] Control the movement trajectories of multiple joints in the robot arm based on the motion path, and plan time sequence actions and real-time obstacle avoidance control;
[0010] Collect the rotation angle and throttle amount of the steering wheel in the ship, and define the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle and throttle amount of the steering wheel in the ship;
[0011] The motion paths of the corresponding joints are defined according to the workload of the throttle robot arm and the steering robot arm to complete the autonomous control of the ship.
[0012] Optionally, when the manipulator and the console are in a communication interaction state, based on detecting the surrounding environment data and the posture data, and defining the motion information of the ship according to the surrounding environment data and the posture data, the method includes:
[0013] Positioning the robotic arm and console;
[0014] Mark the position of the robot arm and the position of the control console, and define the relative distance between the position of the robot arm and the position of the control console;
[0015] The communication mode between the manipulator and the console is defined according to the relative distance and the communication strength of the ship, and the communication interaction state between the manipulator and the console is realized by using the communication mode;
[0016] Collect the ship's surrounding environment data and attitude data;
[0017] The state of the ship is defined based on the surrounding environment data and posture data of the ship, and corresponding action information is triggered based on the state of the ship.
[0018] Optionally, matching the motion instructions of the robot arm according to the motion information of the ship includes:
[0019] Freeze the ship's motion information;
[0020] Define multiple action nodes based on the action information of the ship, and mark the sub-action information of each action node;
[0021] Match the corresponding action positions according to the sub-action information of each action node, and build an action position set;
[0022] Constructing a sequential table of action positions based on the action position set;
[0023] Match the action instructions of the robot arm according to the sequence table of action positions.
[0024] Optionally, in the motion instruction of the robot arm, defining the motion path of the robot arm based on the motion instruction includes:
[0025] In the action instructions of the robot arm, freeze the action instructions;
[0026] Match the corresponding mobile node based on the action instruction;
[0027] Building a mobile node set based on multiple mobile nodes;
[0028] Define the movement trajectory of the robot arm based on the set of mobile nodes;
[0029] Define the motion path of the robot arm according to its movement trajectory.
[0030] Optionally, the controlling of the activity trajectories of multiple joints in the robot arm based on the motion path, and planning of time series motions and real-time obstacle avoidance control, includes:
[0031] Freeze the motion path and mark the position in the motion path;
[0032] Freeze the end of the robotic arm and mark the current position of the end of the robotic arm;
[0033] Compare the current position of the end of the robot arm with the position in the motion path;
[0034] Define the starting position of the motion path and collect the relative distance between the current position of the end of the robot arm and the starting position of the motion path;
[0035] Planning a moving trajectory of the end of the robotic arm based on a relative distance between a current position of the end of the robotic arm and a starting position of the motion path, until the end of the robotic arm is at the starting position of the motion path;
[0036] When the end of the robot arm is at the starting position of the motion path, the activity trajectories of multiple joints in the robot arm are regulated according to the motion path;
[0037] The time series actions are planned according to the activity trajectories of multiple joints, and real-time obstacle avoidance control is performed for the robotic arm.
[0038] Optionally, collect time series actions, and define key start-stop actions, reversing actions, and load start-stop actions according to the time series actions; in this case, the time series actions are used as continuous actions;
[0039] During the execution of time series actions,
[0040] The target time series action state is S = [s1, s2, s3, ... s n ],
[0041] The target control quantity sequence is U = [u o1 ,u o2 ,u o3,......u on ],
[0042] Among them, s i is a single action state, i = 1...n, the state quantity includes the angles of each joint in the robot arm and the three-dimensional coordinates and orientation of the end, u oi is a single control quantity, i=1...n, and the control quantity includes the angle control quantity of each joint in the robot arm;
[0043] The control algorithm is
[0044]
[0045] Where u is the angle control quantity of multiple joints, f(u) is the dynamic equation from the angle control quantity to the target position, and in the process of control quantity calculation, the control sequence of the control quantity u is obtained.
[0046] Optionally, the collecting of the rotation angle of the steering wheel and the throttle amount of the ship, and defining the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount of the ship, includes:
[0047] Collect the rotation angle of the steering wheel and the throttle amount in the ship;
[0048] Correlate the rotation angle of the steering wheel and the throttle amount in the ship;
[0049] Defining workload sets according to the rotation angle of the steering wheel and the throttle amount in the ship;
[0050] Divide the workload of the throttle robot arm and the workload of the steering robot arm based on the workload set;
[0051] In the throttle robot arm workload, the throttle robot arm workload is calculated based on the movement trajectory of the throttle robot arm and the corresponding trigger force, and the movement path of the throttle robot arm is clarified;
[0052] In the directional robot arm workload, the directional robot arm workload is calculated based on the movement trajectory of the directional robot arm and the corresponding trigger force, and the movement path of the directional robot arm workload is clarified;
[0053] In addition, the path planning algorithm is designed as:
[0054]
[0055] Where S1 and S2 are the target state time series of the two manipulators, s o1 and o2 is the target state that the two robotic arms want to reach, s 1i and 2i is the current state of the two robotic arms, do is the state where there is an obstacle, r s To avoid the safety distance; avoidance loss function The definition is as follows:
[0056]
[0057] Here a, b, c correspond to the actual input parameters, φ(s 1i ,s 2i ,r s ) corresponds to a=s 1i ,b=s 2i ,c=r s ,ζ>0, which is the avoidance intensity parameter.
[0058] Optionally, the step of defining the corresponding joint motion paths according to the workload of the throttle manipulator arm and the workload of the steering manipulator arm to complete the autonomous control of the ship includes:
[0059] Collect the workload of the throttle robot arm and the steering robot arm;
[0060] Associating the workload of the throttle mechanical arm with the workload of the steering mechanical arm, and controlling the corresponding mechanical arm based on the workload of the throttle mechanical arm and the workload of the steering mechanical arm;
[0061] In the workload of the throttle robot arm, control is performed based on the throttle robot arm and corresponds to the motion path of the joint of the throttle robot arm;
[0062] In the workload of the steering robot, control is performed based on the steering robot and corresponds to the motion path of the joints of the steering robot;
[0063] Associating the motion paths of the joints of the throttle robot arm and the motion paths of the joints of the steering robot arm;
[0064] An avoidance mechanism is constructed according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm, and collision of the throttle robotic arm and the steering robotic arm is avoided. At the same time, autonomous control of the ship is triggered according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm to complete autonomous control of the ship.
[0065] Optionally, the method of defining the corresponding joint motion paths according to the workload of the throttle mechanical arm and the workload of the steering mechanical arm to complete the autonomous control of the ship further includes:
[0066] When the control system needs to send the throttle control amount and the steering wheel control amount, it only needs to use the fitted function for mapping to obtain the action information of the throttle manipulator and the steering manipulator, and send it to the two manipulator controllers; here the cubic B-spline optimization fitting method can be used, and the algorithm is as follows:
[0067]
[0068] Where L d (C(μ), D(p)) is the distance from point D(p) to the cubic B-spline curve C(μ), ρ(μ) is the curvature on the cubic B-spline curve. By solving this minimum optimization problem, the fitted cubic B-spline curve can be obtained;
[0069] In addition, infrared LED lights are placed on the joints and grippers of the throttle robot arm and the steering robot arm. The perception module can measure the positions of the joints and grippers of the throttle robot arm and the steering robot arm by using a binocular vision measurement method and two fixed measuring infrared cameras.
[0070] The depth measurement calculation formula is as follows:
[0071]
[0072] Z(k)=λZ(k)+(1-λ)Z(k-1),
[0073] Where k is the time scale, f is the focal length, T is the camera spacing, λ is the smoothing parameter, and x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera.
[0074] The plane coordinate calculation formula is:
[0075] X(k)=(x l +x r ) / 2,
[0076] Y(k)=(y l +y r ) / 2,
[0077] X(k)=λX(k)+(1-λ)X(k-1),
[0078] Y(k)=λY(k)+(1-λ)Y(k-1),
[0079] where x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera, y l is the Y-axis position of the target point in the left camera, y r is the Y-axis position of the target point in the right camera, and λ is the smoothing parameter, so as to obtain the X, Y, and Z coordinates of each joint and hand grip in the robot arm;
[0080] In the behavior storage, the perception module stores the state information of the key behavior actions of the throttle robot arm and the steering robot arm through two measuring infrared cameras, and then monitors the throttle robot arm and the steering robot arm according to the control instructions issued by the control system. When it is found that the actions made by the throttle robot arm and the steering robot arm deviate from the control instructions issued by the controller, the operation error is sent to the control system, and the control system corrects the action of the robot arm according to the operation error. The calculation method of the action deviation is as follows:
[0081] e(k)=P(k)-P o (k),
[0082]
[0083] Δ=α|u|+βσ,
[0084] Among them, P o The correct time series position for storage [X o ,Y o ,Z o ], P is the real-time action position [X, Y, Z] of each joint of the robot arm, u is the average error, σ is the error variance, Δ is the weighted sum of the average error and the variance, α>0, β>0 are weighted parameters, and the deviation is judged by judging the size of Δ. When Δ is greater than the set value, it is considered that the deviation is too large and intervention is performed.
[0085] In addition, an embodiment of the present invention further provides an autonomous control system of a ship by a robotic arm, wherein the autonomous control system of a ship by a robotic arm comprises:
[0086] The motion information module is used to define the motion information of the ship based on the detection of the surrounding environment data and the posture data when the manipulator and the control console are in a communication interaction state;
[0087] A matching module, used to match the motion instructions of the robot arm according to the motion information of the ship;
[0088] A motion path module, used for defining a motion path of the robot arm based on the motion instruction in the motion instruction of the robot arm;
[0089] The motion module is used to control the activity trajectories of multiple joints in the robot arm based on the motion path, and to plan time series actions and real-time obstacle avoidance control;
[0090] The mechanical arm module is used to collect the rotation angle of the steering wheel and the throttle amount of the ship, and define the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount of the ship;
[0091] The joint module is used to define the motion path of the corresponding joint according to the workload of the throttle robot arm and the workload of the direction robot arm to complete the autonomous control of the ship.
[0092] In an embodiment of the present invention, through the method in the embodiment of the present invention, when the robotic arm and the control console are in a communication and interaction state, based on detecting their surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data; the motion instructions of the robotic arm are matched according to the motion information of the ship; in the motion instructions of the robotic arm, the motion path of the robotic arm is defined based on the motion instructions; the activity trajectories of multiple joints in the robotic arm are regulated based on the motion path, and time series actions and real-time obstacle avoidance control are planned; the rotation angle of the steering wheel and the throttle amount in the ship are collected, and the throttle robotic arm workload and the steering robotic arm workload are defined according to the rotation angle of the steering wheel and the throttle amount in the ship; the motion paths of the corresponding joints are defined according to the throttle robotic arm workload and the steering robotic arm workload, so as to complete the autonomous control of the ship, thereby realizing the control and control of the control console by the robotic arm, and realizing unmanned control of the ship, which has sufficient practical value. BRIEF DESCRIPTION OF THE DRAWINGS
[0093] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0094] Figure 1 is a flow chart of a method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0095] Figure 2 is a flow chart of S11 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0096] Figure 3 is a flow chart of S12 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0097] Figure 4 is a flow chart of S13 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0098] Figure 5 is a flow chart of S14 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0099] Figure 6 is a flow chart of S15 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0100] Figure 7 is a flow chart of S16 in the method for autonomously controlling a ship by a mechanical arm in an embodiment of the present invention;
[0101] Figure 8 is a schematic diagram of the interaction between the manipulator arm and the control console in the method for autonomously controlling a ship by the manipulator arm in an embodiment of the present invention;
[0102] Fig. 9 Schematic diagram of the structure of the autonomous control system of a ship by a mechanical arm in an embodiment of the present invention;
[0103] Fig.10 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0104] 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.
[0105] Method Embodiment
[0106] See also Figures 1 to 10 A method for autonomously controlling a ship by a robot arm is applied to an unmanned control scenario of a ship; the robot arm is at a control console of the ship, and the robot arm and the control console are in a communication interaction state; a method for autonomously controlling a ship by a robot arm comprises:
[0107] Step S11: When the robot arm and the control console are in a communication interaction state, based on detecting the surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data;
[0108] Step S12: matching the motion instructions of the robot arm according to the motion information of the ship;
[0109] Step S13: in the motion instruction of the robot arm, defining the motion path of the robot arm based on the motion instruction;
[0110] Step S14: regulating the activity trajectories of multiple joints in the robotic arm based on the motion path, and planning time series motions and real-time obstacle avoidance control;
[0111] Step S15: collecting the rotation angle of the steering wheel and the throttle amount of the ship, and defining the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount of the ship;
[0112] Step S16: defining the motion paths of the corresponding joints according to the workload of the throttle robot arm and the workload of the steering robot arm to complete the autonomous control of the ship.
[0113] In an embodiment of the present invention, through the method in the embodiment of the present invention, when the robotic arm and the control console are in a communication and interaction state, based on detecting their surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data; the motion instructions of the robotic arm are matched according to the motion information of the ship; in the motion instructions of the robotic arm, the motion path of the robotic arm is defined based on the motion instructions; the activity trajectories of multiple joints in the robotic arm are regulated based on the motion path, and time series actions and real-time obstacle avoidance control are planned; the rotation angle of the steering wheel and the throttle amount in the ship are collected, and the throttle robotic arm workload and the steering robotic arm workload are defined according to the rotation angle of the steering wheel and the throttle amount in the ship; the motion paths of the corresponding joints are defined according to the throttle robotic arm workload and the steering robotic arm workload, so as to complete the autonomous control of the ship, thereby realizing the control and control of the control console by the robotic arm, and realizing unmanned control of the ship, which has sufficient practical value.
[0114] refer to Figure 2 In step S11, when the manipulator and the console are in a communication interaction state, based on detecting the surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data;
[0115] In the specific implementation process of the present invention, the specific steps may be:
[0116] S111: Positioning the robot arm and the console;
[0117] S112: marking the position of the robot arm and the position of the control console, and defining the relative distance between the position of the robot arm and the position of the control console;
[0118] S113: defining a communication mode between the manipulator and the console according to the relative distance and the communication strength of the ship, and using the communication mode to realize a communication interaction state between the manipulator and the console;
[0119] S114: Collecting surrounding environment data and attitude data of the ship;
[0120] S115: Define the state of the ship based on the surrounding environment data and posture data of the ship, and trigger corresponding action information based on the state of the ship.
[0121] In the embodiment of the present application, the manipulator and the console are positioned; the position of the manipulator and the console are marked, and the relative distance between the position of the manipulator and the console is defined, so as to introduce the relative distance between the position of the manipulator and the console, thereby defining the communication mode between the manipulator and the console according to the relative distance and the communication strength of the ship, and using the communication mode to realize the communication interaction state between the manipulator and the console, thereby ensuring the communication interaction state between the manipulator and the console, so as to facilitate the manipulator to control the console. Therefore, the manipulator is at the console of the ship, and the manipulator and the console are in a communication interaction state.
[0122] Furthermore, the surrounding environment data and attitude data of the ship are collected so as to introduce the surrounding environment data and attitude data of the ship, thereby associating the surrounding environment data and attitude data of the ship and controlling the ship according to the surrounding environment and attitude.
[0123] Therefore, the state of the ship is defined based on the ship's surrounding environment data and posture data, and the corresponding action information is triggered based on the ship's state, so that the corresponding state matches the corresponding action, avoiding the ship's capsizing accident. At the same time, autonomous adjustment in different states is achieved to ensure the ship's stability on the water.
[0124] refer to Figure 3 , in step S12, matching the action instructions of the manipulator according to the action information of the ship;
[0125] In the specific implementation process of the present invention, the specific steps may be:
[0126] S121: freeze the motion information of the ship;
[0127] S122: defining multiple action nodes based on the action information of the ship, and marking sub-action information of each action node;
[0128] S123: Matching corresponding action positions according to sub-action information of each action node, and constructing an action position set;
[0129] S124: constructing a sequence table of action positions based on the action position set;
[0130] S125: Matching the action instructions of the robot arm according to the sequence table of the action positions.
[0131] In an embodiment of the present application, the action information of the ship is frozen; multiple action nodes are defined based on the action information of the ship, and sub-action information of each action node is marked, so as to split the action information of the ship into multiple sub-actions, thereby matching the corresponding sub-action information for each action node, and then controlling each sub-action information.
[0132] At this time, the corresponding action position is matched according to the sub-action information of each action node, and an action position set is constructed, so as to construct a corresponding action position set according to multiple action positions, thereby presenting the order of multiple action positions based on the action position set, and then constructing a sequence table of action positions based on the action position set; the action instructions of the manipulator are matched according to the sequence table of action positions, thereby clarifying the action instructions of the manipulator, and thus controlling the manipulator based on the action instructions of the manipulator, ensuring the action interaction of the manipulator and the control console, and realizing unmanned control of the ship.
[0133] refer to Figure 4 , in step S13, in the action instruction of the robot arm, the action path of the robot arm is defined based on the action instruction;
[0134] In the specific implementation process of the present invention, the specific steps may be:
[0135] S131: freeze the action command in the action command of the robot arm;
[0136] S132: Matching a corresponding mobile node based on the action instruction;
[0137] S133: constructing a mobile node set according to the multiple mobile nodes;
[0138] S134: defining a moving trajectory of the robot arm based on the mobile node set;
[0139] S135: defining a motion path of the robot arm according to the movement trajectory of the robot arm.
[0140] In an embodiment of the present application, in the motion instructions of the robotic arm, the motion instructions are frozen and parsed so as to match the corresponding mobile nodes based on the motion instructions, thereby controlling the moving position of the robotic arm according to multiple mobile nodes, and then limiting the moving trajectory of the robotic arm, thereby ensuring the control of the control console by the robotic arm.
[0141] At this time, a mobile node set is constructed based on multiple mobile nodes; the moving trajectory of the robot arm is defined based on the mobile node set; the motion path of the robot arm is defined according to the moving trajectory of the robot arm, thereby ensuring the integrity of the motion path of the robot arm, and autonomous control of the robot arm is achieved based on the motion path of the robot arm, and the offset of the robot arm is limited, thereby ensuring the accuracy of the motion path of the robot arm.
[0142] refer to Figure 5 , S14: Control the activity trajectories of multiple joints in the robot arm based on the motion path, and plan the time series actions and real-time obstacle avoidance control;
[0143] In the specific implementation process of the present invention, the specific steps may be:
[0144] S141: freeze the motion path and mark the position in the motion path;
[0145] S142: freeze the end of the robotic arm and mark the current position of the end of the robotic arm;
[0146] S143: Compare the current position of the end of the robot arm with the position in the motion path;
[0147] S144: defining the starting position of the motion path, and collecting the relative distance between the current position of the end of the robot arm and the starting position of the motion path;
[0148] S145: planning a moving trajectory of the end of the robotic arm based on a relative distance between a current position of the end of the robotic arm and a starting position of the motion path, until the end of the robotic arm is at the starting position of the motion path;
[0149] S146: When the end of the robotic arm is at the starting position of the motion path, regulating the activity trajectories of the plurality of joints in the robotic arm according to the motion path;
[0150] S147: Plan time series actions based on the activity trajectories of multiple joints, and perform real-time obstacle avoidance control for the robotic arm.
[0151] In an embodiment of the present application, the motion path is frozen and the position in the motion path is marked; the end of the robotic arm is frozen and the current position of the end of the robotic arm is marked, so as to compare the current position of the end of the robotic arm with the position in the motion path, thereby performing corresponding position control on the current position of the end of the robotic arm.
[0152] At this time, the starting position of the motion path is defined, and the relative distance between the current position of the end of the robot arm and the starting position of the motion path is collected; the movement trajectory of the end of the robot arm is planned based on the relative distance between the current position of the end of the robot arm and the starting position of the motion path until the end of the robot arm is at the starting position of the motion path, so as to facilitate the position zeroing of the end of the robot arm, thereby performing action based on the starting position of the motion path, thereby ensuring the accuracy of the movement of the end of the robot arm.
[0153] Furthermore, when the end of the robotic arm is at the starting position of the motion path, the activity trajectories of multiple joints in the robotic arm are regulated according to the motion path; time series actions are planned according to the activity trajectories of multiple joints, so as to perform corresponding time-actions for the time series actions, thereby controlling the position adjustment of multiple joints under the overall motion coordination, and performing real-time obstacle avoidance control for the robotic arm, ensuring the smoothness of the movements between multiple joints, and further ensuring the position accuracy of the end of the robotic arm.
[0154] Therefore, the control of the activity trajectories of multiple joints in the robot arm based on the motion path, and planning of time series actions and real-time obstacle avoidance control also includes:
[0155] Collect time series actions, and define key start-stop actions, reversing actions, and load start-stop actions based on the time series actions; at this time, the time series actions are regarded as continuous actions;
[0156] During the execution of time series actions,
[0157] The target time series action state is S = [s1, s2, s3, ... s n ],
[0158] The target control quantity sequence is U = [u o1 ,u o2 ,u o3 ,......u on ],
[0159] Among them, s i is a single action state, i = 1...n, the state quantity includes the angles of each joint in the robot arm and the three-dimensional coordinates and orientation of the end, u oi is a single control quantity, i=1...n, and the control quantity includes the angle control quantity of each joint in the robot arm;
[0160] The control algorithm is
[0161]
[0162] Where i is the angle control quantity of multiple joints, f(u) is the dynamic equation from the angle control quantity to the target position, and in the process of control quantity calculation, the control sequence of the control quantity u is obtained.
[0163] refer to Figure 6 , S15: collecting the rotation angle of the steering wheel and the throttle amount of the ship, and defining the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount of the ship;
[0164] In the specific implementation process of the present invention, the specific steps may be:
[0165] S151: Collect the rotation angle and throttle value of the steering wheel in the ship;
[0166] S152: Associate the rotation angle of the steering wheel and the throttle amount in the ship;
[0167] S153: defining a workload set according to a rotation angle of a steering wheel and a throttle amount in the ship;
[0168] S154: Dividing the workload of the throttle robot arm and the workload of the steering robot arm based on the workload set;
[0169] S155: In the throttle mechanical arm workload, the throttle mechanical arm workload is calculated based on the movement trajectory of the throttle mechanical arm and the corresponding trigger force, and the movement path of the throttle mechanical arm is clarified;
[0170] S156: In the directional robot arm workload, the directional robot arm workload is calculated based on the moving trajectory of the directional robot arm and the corresponding trigger force, and the moving path of the directional robot arm workload is clarified.
[0171] In an embodiment of the present application, the rotation angle of the steering wheel and the throttle amount in the ship are collected; the rotation angle of the steering wheel and the throttle amount in the ship are associated; and a workload set is defined according to the rotation angle of the steering wheel and the throttle amount in the ship, so as to manage and control the workload set.
[0172] At this time, the throttle robot arm workload and the steering robot arm workload are divided based on the workload set, and corresponding management and control are performed on the throttle robot arm workload and the steering robot arm workload. At this time, in the throttle robot arm workload, the throttle robot arm workload is calculated based on the moving trajectory of the throttle robot arm and the corresponding trigger force, and the moving path of the throttle robot arm is clarified; in the steering robot arm workload, the steering robot arm workload is calculated based on the moving trajectory of the steering robot arm and the corresponding trigger force, and the moving path of the steering robot arm workload is clarified.
[0173] Therefore, the throttle robotic arm and the steering robotic arm control different parts respectively, and perform separate management on the throttle and the direction. The coordinated management of the throttle and the direction is triggered based on the interaction between the throttle robotic arm and the steering robotic arm, ensuring a timely response to the throttle and the direction.
[0174] In addition, the path planning algorithm is designed as:
[0175]
[0176] Where S1 and S2 are the target state time series of the two manipulators, s o1 and o2 is the target state that the two robotic arms want to reach, s 1i and2i is the current state of the two robotic arms, d o is the state where there is an obstacle, r s To avoid the safety distance; avoidance loss function The definition is as follows:
[0177]
[0178] Here a, b, c correspond to the actual input parameters, φ(s 1i ,s 2i ,r s ) corresponds to a=s 1i ,b=s 2i ,c=r s ,ζ>0, which is the avoidance intensity parameter.
[0179] At this time, the robotic arm has the ability to plan motion. When it receives a new motion instruction, it plans a reasonable time series motion for each joint and gripper based on the spatial constraints and terminal constraints to prevent the robotic arm from colliding with existing objects or the two robotic arms from colliding with each other, thereby achieving smooth transition of motion.
[0180] In addition, the path planning algorithm first constructs an optimization problem as follows:
[0181]
[0182] in where is the obstacle avoidance loss function, and then solve the optimization problem to obtain the control amount u, where r s is the avoidance safety distance, r o In addition, the path planning algorithm may be A*, D*, TEB and other algorithms, and the motion control algorithm may be PID, adaptive control, fuzzy control, predictive control and other algorithms.
[0183] refer to Figure 7 , S16: defining the motion path of the corresponding joint according to the workload of the throttle manipulator arm and the workload of the direction manipulator arm to complete the autonomous control of the ship;
[0184] In the specific implementation process of the present invention, the specific steps may be:
[0185] S161: collecting the workload of the throttle robot arm and the workload of the steering robot arm;
[0186] S162: Associating the workload of the throttle mechanical arm with the workload of the steering mechanical arm, and controlling the corresponding mechanical arm based on the workload of the throttle mechanical arm and the workload of the steering mechanical arm;
[0187] S163: In the workload of the throttle mechanical arm, control is performed based on the throttle mechanical arm, and the motion path of the joint of the throttle mechanical arm is corresponding;
[0188] S164: In the workload of the steering robot arm, control is performed based on the steering robot arm, and the motion path of the joint of the steering robot arm is corresponded;
[0189] S165: Associating the motion path of the joint of the throttle robot arm and the motion path of the joint of the steering robot arm;
[0190] S166: An avoidance mechanism is constructed according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm, and collision of the throttle robotic arm and the steering robotic arm is avoided. At the same time, autonomous control of the ship is triggered according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm to complete autonomous control of the ship.
[0191] In the specific implementation process of the present invention, the workload of the throttle mechanical arm and the workload of the steering mechanical arm are collected; the workload of the throttle mechanical arm and the workload of the steering mechanical arm are associated, and the corresponding mechanical arm is controlled based on the workload of the throttle mechanical arm and the workload of the steering mechanical arm.
[0192] At this time, in the workload of the throttle robotic arm, control is carried out based on the throttle robotic arm, and corresponds to the motion path of the joints of the throttle robotic arm; in the workload of the steering robotic arm, control is carried out based on the steering robotic arm, and corresponds to the motion path of the joints of the steering robotic arm, so as to control the motion path of the joints of the steering robotic arm and the motion path of the joints of the throttle robotic arm, thereby comparing the motion path of the joints of the steering robotic arm and the motion path of the joints of the throttle robotic arm, avoiding conflicting positions in the motion paths of the joints of the steering robotic arm and the motion paths of the joints of the throttle robotic arm.
[0193] Furthermore, the motion paths of the joints of the throttle mechanical arm and the motion paths of the joints of the steering mechanical arm are associated; an avoidance mechanism is constructed according to the motion paths of the joints of the throttle mechanical arm and the motion paths of the joints of the steering mechanical arm, and the collision of the throttle mechanical arm and the steering mechanical arm is avoided; at the same time, autonomous control of the ship is triggered according to the motion paths of the joints of the throttle mechanical arm and the motion paths of the joints of the steering mechanical arm, so as to complete the autonomous control of the ship
[0194] Therefore, the rotation angle of the steering wheel and the throttle amount of the ship are collected, and the workload of the throttle robotic arm and the steering robotic arm are defined according to the rotation angle of the steering wheel and the throttle amount of the ship; the motion paths of the corresponding joints are defined according to the workload of the throttle robotic arm and the steering robotic arm to complete the autonomous control of the ship, and then the control of the console by the robotic arm is realized, realizing unmanned control of the ship, which has sufficient practical value.
[0195] The method further comprises defining the motion paths of the corresponding joints according to the workload of the throttle mechanical arm and the workload of the steering mechanical arm to complete the autonomous control of the ship.
[0196] When the control system needs to send the throttle control amount and the steering wheel control amount, it only needs to use the fitted function for mapping to obtain the action information of the throttle manipulator and the steering manipulator, and send it to the two manipulator controllers; here the cubic B-spline optimization fitting method can be used, and the algorithm is as follows:
[0197]
[0198]
[0199] Where L d (C(μ), D(p)) is the distance from point D(p) to the cubic B-spline curve C(μ), ρ(μ) is the curvature on the cubic B-spline curve. By solving this minimum optimization problem, the fitted cubic B-spline curve can be obtained;
[0200] In addition, infrared LED lights are placed on the joints and grippers of the throttle robot arm and the steering robot arm. The perception module can measure the positions of the joints and grippers of the throttle robot arm and the steering robot arm by using a binocular vision measurement method and two fixed measuring infrared cameras.
[0201] The depth measurement calculation formula is as follows:
[0202]
[0203] Z(k)=λZ(k)+(1-λ)Z(k-1),
[0204] Where k is the time scale, f is the focal length, T is the camera spacing, λ is the smoothing parameter, and x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera.
[0205] The plane coordinate calculation formula is:
[0206] X(k)=(x l +x r ) / 2,
[0207] Y(k)=(y l +y r ) / 2,
[0208] X(k)=λX(k)+(1-λ)X(k-1),
[0209] Y(k)=λY(k)+(1-λ)Y(k-1),
[0210] where x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera, y l is the Y-axis position of the target point in the left camera, y r is the Y-axis position of the target point in the right camera, and λ is the smoothing parameter, so as to obtain the X, Y, and Z coordinates of each joint and hand grip in the robot arm;
[0211] In the behavior storage, the perception module stores the state information of the key behavior actions of the throttle robot arm and the steering robot arm through two measuring infrared cameras, and then monitors the throttle robot arm and the steering robot arm according to the control instructions issued by the control system. When it is found that the actions made by the throttle robot arm and the steering robot arm deviate from the control instructions issued by the controller, the operation error is sent to the control system, and the control system corrects the action of the robot arm according to the operation error. The calculation method of the action deviation is as follows:
[0212] e(k)=P(k)-P o (k),
[0213]
[0214] Δ=α|u|+βσ,
[0215] Among them, P o The correct time series position for storage [X o ,Y o ,Z o ], P is the real-time action position [X, Y, Z] of each joint of the robot arm, u is the average error, σ is the error variance, Δ is the weighted sum of the average error and the variance, α>0, β>0 are weighted parameters, and the deviation is judged by judging the size of Δ. When Δ is greater than the set value, it is considered that the deviation is too large and intervention is performed.
[0216] Furthermore, when the robotic arm and the control console are in a communication and interactive state, based on detecting the surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data; the motion instructions of the robotic arm are matched according to the motion information of the ship; in the motion instructions of the robotic arm, the motion path of the robotic arm is defined based on the motion instructions; the activity trajectories of multiple joints in the robotic arm are regulated based on the motion path, and time series actions and real-time obstacle avoidance control are planned; the rotation angle of the steering wheel and the throttle amount in the ship are collected, and the throttle robotic arm workload and the steering robotic arm workload are defined according to the rotation angle of the steering wheel and the throttle amount in the ship; the motion paths of the corresponding joints are defined according to the throttle robotic arm workload and the steering robotic arm workload, so as to complete the autonomous control of the ship, thereby realizing the control of the control console by the robotic arm and realizing unmanned control of the ship, which has sufficient practical value.
[0217] Specific:
[0218] The console consists of buttons, joystick handles, display screens, and data processing modules;
[0219] As the core control part of the ship, the autonomous control box includes a perception module, an inertial navigation module, a communication module, a data acquisition module and a decision controller;
[0220] The robotic arm comprises a throttle robotic arm and a steering wheel robotic arm, and both the throttle robotic arm and the steering wheel robotic arm are composed of a first joint, a second joint, a third joint, an arm joint, a gripper and a robotic arm controller.
[0221] At this time, the autonomous control box is placed under the console. Its perception module obtains information about the ship's surrounding environment and transmits it to the decision-making controller. The inertial navigation module obtains data such as the ship's position, speed, and attitude and transmits it to the decision-making controller. The communication module obtains command data and transmits it to the decision-making controller. The decision-making controller receives the control command and then uses the planning algorithm and control algorithm to calculate the ship's motion information based on the ship's current attitude and environmental information, and then transmits the ship's motion information to the robotic arm.
[0222] The throttle manipulator is placed in front of the ship's throttle push rod, and can control the ship's start and stop, throttle, reverse, load button, etc. The steering wheel manipulator is placed in front of the ship's steering wheel, and can control the ship's steering wheel, thrust motor throttle, etc. The interactive panel is placed on the console, mainly to complete the humanized interaction between the operator and the autonomous control box, and to realize the setting and execution of the manipulator's actions. The ship can be a traditional fishing boat, a cruise ship, or a commercial ship, which is not limited here.
[0223] When working, the operator first determines the corresponding actions of the throttle manipulator arm and the steering manipulator arm through the interactive panel, such as start and stop, throttle amount, load action, steering wheel angle, thrust motor throttle amount, etc., and then stores the positions of the manipulator arms corresponding to these actions. During the autonomous control of the ship, the autonomous control box identifies the surrounding environment, plans the navigation trajectory according to the received tasks, and then uses the trajectory tracking control algorithm to calculate the throttle amount and angle required for the ship. Then, the execution position of the throttle manipulator arm and the steering manipulator arm is obtained from the relationship between the stored manipulator arm position and the action amount, and sent to the manipulator arm to implement the operation, thereby completing the unmanned control of the ship.
[0224] In the embodiment of the present invention, by acquiring the sensing data, inertial navigation data, and command data, the throttle mechanical arm and the steering mechanical arm are controlled in real time, so that the ship moves along the set command and realizes the autonomous navigation of the ship. The specific steps are as follows:
[0225] Step 1: The operator sends instructions to the autonomous control box through the interactive panel to control the throttle manipulator and the steering manipulator so that the two manipulators can complete certain specific actions, such as starting and stopping the ship, throttle control, steering control, etc., and then sets the manipulator controller to encode and store these specific actions one-to-one, and sends the stored data to the autonomous control box. The control box stores the encoded actions and builds a mapping relationship between the manipulator action information and the throttle amount and steering wheel angle;
[0226] Step 2: The autonomous control box obtains the corresponding data through the perception module, inertial navigation module, communication module, and data collector, and then plans a reasonable path in the perceived environment according to the command information, and then uses the motion control algorithm to calculate the rotation angle of the ship's steering wheel and the throttle amount;
[0227] Step 3: Based on the constructed robot arm motion information, throttle amount and steering wheel angle, the autonomous control box calculates the required steering wheel rotation angle and throttle amount of the ship, calculates the robot arm motion amount and sends it to the two robot arms;
[0228] Step 3: Based on the constructed robot arm motion information, throttle amount and steering wheel angle, the autonomous control box calculates the required steering wheel rotation angle and throttle amount of the ship, calculates the robot arm motion amount and sends it to the two robot arms;
[0229] Step 4: After receiving the command data, the throttle robot arm and the steering robot arm control the joints and grippers to complete the corresponding actions, thereby completing the control of the ship.
[0230] System Example
[0231] See also Fig. 9 , Fig. 9It is a schematic diagram of the structural composition of the autonomous control system of a ship by a robotic arm in an embodiment of the present invention.
[0232] like Fig. 9 As shown, a robot arm autonomously controls a ship, and the robot arm autonomously controls a ship, comprising:
[0233] The motion information module 21 is used to define the motion information of the ship based on the detection of the surrounding environment data and the posture data when the manipulator and the control console are in a communication interaction state;
[0234] A matching module 22, used for matching the motion instructions of the robot arm according to the motion information of the ship;
[0235] A motion path module 23, used for defining a motion path of the robot arm based on the motion instruction in the motion instruction of the robot arm;
[0236] The action module 24 is used to control the activity trajectories of multiple joints in the robot arm based on the action path, and plan the time series actions and real-time obstacle avoidance control;
[0237] The mechanical arm module 25 is used to collect the rotation angle of the steering wheel and the throttle amount in the ship, and define the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount in the ship;
[0238] The joint module 26 is used to define the motion path of the corresponding joint according to the workload of the throttle robot arm and the workload of the steering robot arm to complete the autonomous control of the ship.
[0239] Example
[0240] See also Fig.10 , refer to the following Fig.10 The electronic device 40 according to this embodiment of the present invention will be described. Fig.10 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0241] like Fig.10 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).
[0242] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.
[0243] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .
[0244] The storage unit 42 may also include a program / utility 424 having a set (at least one) of joint modules 425, such joint modules 425 including but not limited to: an operating system, one or more application programs, other joint modules and program data, each of which or some combination may include the implementation of a network environment.
[0245] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0246] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 45. Fig.10 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig.10 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.
[0247] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
[0248] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.
[0249] In addition, the above is a detailed introduction to the method and system for autonomous control of a ship by a robotic arm provided in an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A method for autonomously controlling a ship by a robotic arm, It is characterized in that Applied to the unmanned control scenario of ships; the robotic arm is at the control console of the ship, and the robotic arm and the control console are in a communication interaction state The method for autonomously controlling a ship by the mechanical arm comprises: When the manipulator and the control console are in a communication interaction state, based on detecting the surrounding environment data and posture data, the motion information of the ship is defined according to the surrounding environment data and posture data; Match the action instructions of the robotic arm according to the action information of the ship; In the motion instruction of the robot arm, a motion path of the robot arm is defined based on the motion instruction; Control the movement trajectories of multiple joints in the robot arm based on the motion path, and plan time sequence actions and real-time obstacle avoidance control; Collect the rotation angle and throttle amount of the steering wheel in the ship, and define the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle and throttle amount of the steering wheel in the ship; The motion paths of the corresponding joints are defined according to the workload of the throttle robot arm and the steering robot arm to complete the autonomous control of the ship.
2. The method for autonomously controlling a ship by a robotic arm according to claim 1, It is characterized in that When the manipulator and the console are in a communication interaction state, based on detecting the surrounding environment data and the posture data, the motion information of the ship is defined according to the surrounding environment data and the posture data, including: Positioning the robotic arm and console; Mark the position of the robot arm and the position of the control console, and define the relative distance between the position of the robot arm and the position of the control console; The communication mode between the manipulator and the console is defined according to the relative distance and the communication strength of the ship, and the communication interaction state between the manipulator and the console is realized by using the communication mode; Collect the ship's surrounding environment data and attitude data; The state of the ship is defined based on the surrounding environment data and posture data of the ship, and corresponding action information is triggered based on the state of the ship.
3. The method for autonomously controlling a ship by a robotic arm according to claim 2, It is characterized in that The matching of the motion instructions of the robot arm according to the motion information of the ship includes: Freeze the ship's motion information; Define multiple action nodes based on the action information of the ship, and mark the sub-action information of each action node; Match the corresponding action positions according to the sub-action information of each action node, and build an action position set; Constructing a sequential table of action positions based on the action position set; Match the action instructions of the robot arm according to the sequence table of action positions.
4. The method for autonomously controlling a ship by a mechanical arm according to claim 1, It is characterized in that In the motion instruction of the robot arm, defining the motion path of the robot arm based on the motion instruction includes: In the action instructions of the robot arm, freeze the action instructions; Match the corresponding mobile node based on the action instruction; Building a mobile node set based on multiple mobile nodes; Define the movement trajectory of the robot arm based on the set of mobile nodes; Define the motion path of the robot arm according to its movement trajectory.
5. The method for autonomously controlling a ship by a mechanical arm according to claim 1, It is characterized in that The motion path-based control of the activity trajectories of multiple joints in the robotic arm, and planning of time series motions and real-time obstacle avoidance control, includes: Freeze the motion path and mark the position in the motion path; Freeze the end of the robotic arm and mark the current position of the end of the robotic arm; Compare the current position of the end of the robot arm with the position in the motion path; Define the starting position of the motion path and collect the relative distance between the current position of the end of the robot arm and the starting position of the motion path; Planning a moving trajectory of the end of the robotic arm based on a relative distance between a current position of the end of the robotic arm and a starting position of the motion path, until the end of the robotic arm is at the starting position of the motion path; When the end of the robot arm is at the starting position of the motion path, the activity trajectories of multiple joints in the robot arm are regulated according to the motion path; The time series actions are planned according to the activity trajectories of multiple joints, and real-time obstacle avoidance control is performed for the robotic arm.
6. The method for autonomously controlling a ship by a mechanical arm according to claim 5, It is characterized in that The method of controlling the activity trajectories of multiple joints in the robot arm based on the motion path, and planning time series motions and real-time obstacle avoidance control, further includes: Collect time series actions, and define key start-stop actions, reversing actions, and load start-stop actions based on the time series actions; at this time, the time series actions are regarded as continuous actions; During the execution of time series actions, The target time series action state is S = [s 1 ,s 2 ,s 3 ,......s n ], The target control quantity sequence is U = [u o1 ,u o2 ,u o3 ,......u on ], Among them, s i is a single action state, i = 1...n, the state quantity includes the angles of each joint in the robot arm and the three-dimensional coordinates and orientation of the end, u oi is a single control quantity, i=1...n, and the control quantity includes the angle control quantity of each joint in the robot arm; The control algorithm is Where u is the angle control quantity of multiple joints, f(u) is the dynamic equation from the angle control quantity to the target position, and in the process of control quantity calculation, the control sequence of the control quantity u is obtained.
7. The method for autonomously controlling a ship by a mechanical arm according to claim 6, It is characterized in that The collecting of the rotation angle of the steering wheel and the throttle amount in the ship, and defining the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount in the ship, include: Collect the rotation angle of the steering wheel and the throttle amount in the ship; Correlate the rotation angle of the steering wheel and the throttle amount in the ship; Defining workload sets according to the rotation angle of the steering wheel and the throttle amount in the ship; Divide the workload of the throttle robot arm and the workload of the steering robot arm based on the workload set; In the throttle robot arm workload, the throttle robot arm workload is calculated based on the movement trajectory of the throttle robot arm and the corresponding trigger force, and the movement path of the throttle robot arm is clarified; In the directional robot arm workload, the directional robot arm workload is calculated based on the movement trajectory of the directional robot arm and the corresponding trigger force, and the movement path of the directional robot arm workload is clarified; In addition, the path planning algorithm is designed as: Where S 1 ,S 2 is the target state time series of the two robotic arms, s o1 and o2 is the target state that the two robotic arms want to reach, s 1i and 2i is the current state of the two robotic arms, d o is the state where there is an obstacle, r s To avoid the safety distance; avoidance loss function The definition is as follows: Here a, b, c correspond to the actual input parameters, φ(s 1i ,s 2i ,r s ) corresponds to a=s 1i ,b=s 2i ,c=r s ,ζ>0, which is the avoidance intensity parameter.
8. The method for autonomously controlling a ship by a mechanical arm according to claim 1, It is characterized in that Defining the corresponding joint motion paths according to the workload of the throttle mechanical arm and the workload of the steering mechanical arm to complete the autonomous control of the ship includes: Collect the workload of the throttle robot arm and the steering robot arm; Associating the workload of the throttle mechanical arm with the workload of the steering mechanical arm, and controlling the corresponding mechanical arm based on the workload of the throttle mechanical arm and the workload of the steering mechanical arm; In the workload of the throttle robot arm, control is performed based on the throttle robot arm and corresponds to the motion path of the joint of the throttle robot arm; In the workload of the steering robot, control is performed based on the steering robot and corresponds to the motion path of the joints of the steering robot; Associating the motion paths of the joints of the throttle robot arm and the motion paths of the joints of the steering robot arm; An avoidance mechanism is constructed according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm, and collision of the throttle robotic arm and the steering robotic arm is avoided. At the same time, autonomous control of the ship is triggered according to the motion paths of the joints of the throttle robotic arm and the motion paths of the joints of the steering robotic arm to complete autonomous control of the ship.
9. The method for autonomously controlling a ship by a mechanical arm according to claim 8, It is characterized in that The method further comprises defining the motion paths of the corresponding joints according to the workload of the throttle mechanical arm and the workload of the steering mechanical arm to complete the autonomous control of the ship. When the control system needs to send the throttle control amount and the steering wheel control amount, it only needs to use the fitted function for mapping to obtain the action information of the throttle manipulator and the steering manipulator, and send it to the two manipulator controllers; here the cubic B-spline optimization fitting method can be used, and the algorithm is as follows: I p =∫ 0 1 L d (C(μ),D(p))+β ρ (μ)dμ Where L d (C(μ), D(p)) is the distance from point D(p) to the cubic B-spline curve C(μ), ρ(μ) is the curvature on the cubic B-spline curve. By solving this minimum optimization problem, the fitted cubic B-spline curve can be obtained; In addition, infrared LED lights are placed on the joints and grippers of the throttle robot arm and the steering robot arm. The perception module can measure the positions of the joints and grippers of the throttle robot arm and the steering robot arm by using a binocular vision measurement method and two fixed measuring infrared cameras. The depth measurement calculation formula is as follows: Z(k)=λZ(k)+(1-λ)Z(k-1), Where k is the time scale, f is the focal length, T is the camera spacing, λ is the smoothing parameter, and x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera. The plane coordinate calculation formula is: X(k)=(x l +x r ) / 2, Y(k)=(y l +y r ) / 2, X(k)=λX(k)+(1-λ)X(k-1), Y(k)=λY(k)+(1-λ)Y(k-1), where x l is the X-axis position of the target point in the left camera, x r is the X-axis position of the target point in the right camera, y l is the Y-axis position of the target point in the left camera, y r is the Y-axis position of the target point in the right camera, and λ is the smoothing parameter, so as to obtain the X, Y, and Z coordinates of each joint and hand grip in the robot arm; In the behavior storage, the perception module stores the state information of the key behavior actions of the throttle robot arm and the steering robot arm through two measuring infrared cameras, and then monitors the throttle robot arm and the steering robot arm according to the control instructions issued by the control system. When it is found that the actions made by the throttle robot arm and the steering robot arm deviate from the control instructions issued by the controller, the operation error is sent to the control system, and the control system corrects the action of the robot arm according to the operation error. The calculation method of the action deviation is as follows: e(k)=P(k)-P o (k), Δ=α|u|+βσ, Among them, P o The correct time series position for storage [X o ,Y o ,Z o ], P is the real-time action position [X, Y, Z] of each joint of the robot arm, u is the average error, σ is the error variance, Δ is the weighted sum of the average error and the variance, α>0, β>0 are weighted parameters, and the deviation is judged by judging the size of Δ. When Δ is greater than the set value, it is considered that the deviation is too large and intervention is performed.
10. An autonomous ship control system using a robotic arm. It is characterized in that The autonomous control system of the ship by the manipulator arm is applied to the autonomous control method of the ship by the manipulator arm as claimed in any one of claims 1 to 9, and the autonomous control system of the ship by the manipulator arm comprises: The motion information module is used to define the motion information of the ship based on the detection of the surrounding environment data and the posture data when the manipulator and the control console are in a communication interaction state; A matching module, used to match the motion instructions of the robot arm according to the motion information of the ship; A motion path module, used for defining a motion path of the robot arm based on the motion instruction in the motion instruction of the robot arm; The motion module is used to control the activity trajectories of multiple joints in the robot arm based on the motion path, and to plan time series actions and real-time obstacle avoidance control; The mechanical arm module is used to collect the rotation angle of the steering wheel and the throttle amount of the ship, and define the workload of the throttle mechanical arm and the workload of the steering mechanical arm according to the rotation angle of the steering wheel and the throttle amount of the ship; The joint module is used to define the motion path of the corresponding joint according to the workload of the throttle robot arm and the workload of the direction robot arm to complete the autonomous control of the ship.
