CN-121973242-A - Sensor-based man-machine collaborative monitoring Internet of things system, method and medium

CN121973242ACN 121973242 ACN121973242 ACN 121973242ACN-121973242-A

Abstract

The invention provides a sensor-based man-machine collaborative monitoring Internet of things system, a method and a medium, relates to the technical field of man-machine cooperative security. The method comprises the steps of obtaining monitoring data of a working area of the cooperative robot, determining a collision risk value based on the monitoring data, a first motion track of an operator and a second motion track of the cooperative robot, determining an avoidance parameter based on the monitoring data, the first motion track, the collision risk value, collision urgency and a moving space range of the cooperative robot, generating a motion control instruction based on the avoidance parameter, and sending the motion control instruction to a motion control system of the cooperative robot, wherein the motion control system adjusts a physical driving signal to drive a mechanical connecting rod to generate compound motion based on the motion control instruction, so that an end effector can avoid. The Internet of things system comprises a collaborative supervision management platform, and the method operates after the computer instructions stored by a computer readable storage medium are read. The invention can improve the safety and efficiency of man-machine cooperation.

Inventors

SHAO ZEHUA
LI YONG
LIU BIN
QUAN YAQIANG
SU CHANG

Assignees

成都秦川物联网科技股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260402

Claims (9)

1. A man-machine cooperative monitoring internet of things system based on a sensor is characterized by comprising a cooperative supervision management platform; The collaborative supervisory management platform is configured to: acquiring monitoring data of a working area of the cooperative robot; determining a collision risk value based on the monitoring data, a first motion trajectory of an operator, and a second motion trajectory of the collaborative robot; determining evasion parameters of the cooperative robot based on the monitoring data, the first motion trail, the collision risk value, the collision urgency and the movement space range of the cooperative robot, and Generating a motion control instruction based on the avoidance parameters, and sending the motion control instruction to a motion control system of the cooperative robot; the motion control system is configured to adjust physical drive signals applied to the joint motors based on the motion control instructions to drive the mechanical links of the collaborative robot to produce a compound motion that causes the end effector to complete evasion.
2. The system of claim 1, wherein the collaborative supervisory management platform is further configured to: Determining a first collision risk value based on the monitoring data; Acquiring a first track set and a second track set based on the first motion track and the second motion track; constructing a first envelope volume set and a second envelope volume set based on the first track set, the second track set and an envelope radius; determining an intrusion depth set based on the first envelope volume set and the second envelope volume set; Determining a second collision risk value based on the intrusion depth set, and The collision risk value is determined by a weighted summation process based on the first collision risk value and the second collision risk value.
3. The system of claim 1, wherein the collaborative supervisory management platform is further configured to: And predicting the first motion track through a sequence prediction model based on the monitoring data and the preset state data of the operator, wherein the sequence prediction model is a machine learning model.
4. The system of claim 1, wherein the collaborative supervisory management platform is further configured to: determining an avoidance target based on the task type; and determining the avoidance parameters through a path planning algorithm based on the monitoring data, the first motion trail, the collision risk value, the collision urgency, the moving space range and the avoidance target.
5. A sensor-based human-machine collaborative monitoring method, wherein the method is performed by a collaborative supervisory management platform in a sensor-based human-machine collaborative monitoring internet of things system, the method comprising: acquiring monitoring data of a working area of the cooperative robot; determining a collision risk value based on the monitoring data, a first motion trajectory of an operator, and a second motion trajectory of the collaborative robot; determining evasion parameters of the cooperative robot based on the monitoring data, the first motion trail, the collision risk value, the collision urgency and the movement space range of the cooperative robot, and Generating a motion control instruction based on the avoidance parameters, and sending the motion control instruction to a motion control system of the cooperative robot; the motion control system is configured to adjust physical drive signals applied to the joint motors based on the motion control instructions to drive the mechanical links of the collaborative robot to produce a compound motion that causes the end effector to complete evasion.
6. The method of claim 5, wherein the determining a collision risk value based on the monitoring data, a first motion profile of an operator, and a second motion profile of the collaborative robot further comprises: Determining a first collision risk value based on the monitoring data; Acquiring a first track set and a second track set based on the first motion track and the second motion track; constructing a first envelope volume set and a second envelope volume set based on the first track set, the second track set and an envelope radius; determining an intrusion depth set based on the first envelope volume set and the second envelope volume set; Determining a second collision risk value based on the intrusion depth set, and The collision risk value is determined by a weighted summation process based on the first collision risk value and the second collision risk value.
7. The method of claim 5, wherein the method further comprises: And predicting the first motion track through a sequence prediction model based on the monitoring data and the preset state data of the operator, wherein the sequence prediction model is a machine learning model.
8. The method of claim 5, wherein the determining avoidance parameters of the collaborative robot based on the monitored data, the first motion profile, the collision risk value, collision urgency, and a range of movement space of the collaborative robot comprises: determining an avoidance target based on the task type; and determining the avoidance parameters through a path planning algorithm based on the monitoring data, the first motion trail, the collision risk value, the collision urgency, the moving space range and the avoidance target.
9. A computer readable storage medium storing computer instructions which, when read by a computer, perform the sensor-based human-machine collaborative monitoring method of claim 5.

Description

Sensor-based man-machine collaborative monitoring Internet of things system, method and medium Technical Field The invention relates to the technical field of man-machine cooperative security, in particular to a man-machine cooperative monitoring Internet of things system, method and medium based on a sensor. Background At present, collaborative robots are introduced in a large number in a plurality of industrial fields, the collaborative robots and operators share the same physical space, and in order to ensure the safety and the working efficiency of man-machine collaboration, the collaborative robots are particularly important to monitor the man-machine collaboration. At present, the man-machine cooperative monitoring system generally has the problems of single sensing means and poor robustness, is easy to produce false alarm or missing alarm under complex industrial environments such as illumination change, metal reflection and the like, cannot sense and adapt to different operation task scenes, causes lag of safety response and hard man-machine interaction, and is difficult to balance between ensuring absolute safety and realizing efficient and smooth cooperative operation. Therefore, there is an urgent need to provide a system, a method and a medium for monitoring the internet of things by using man-machine cooperation based on a sensor, which solve the problems that the man-machine cooperation monitoring system is inaccurate in perception, lack in prejudgment capability and cannot adapt to dynamic tasks, and realize full-process automation from perception, decision-making to execution so as to remarkably improve the safety and the working efficiency of man-machine cooperation. Disclosure of Invention The invention provides a sensor-based man-machine collaborative monitoring Internet of things system, a sensor-based man-machine collaborative monitoring method and a sensor-based man-machine collaborative monitoring Internet of things medium, which aim to solve the problems that a man-machine collaborative monitoring system is inaccurate in perception, lack in prejudgment capability and cannot adapt to dynamic tasks. The system comprises a collaborative supervisory management platform, wherein the collaborative supervisory management platform is configured to acquire monitoring data of a working area of a collaborative robot, determine a collision risk value based on the monitoring data, a first motion track of an operator and a second motion track of the collaborative robot, determine avoidance parameters of the collaborative robot based on the monitoring data, the first motion track, the collision risk value, collision urgency and a movement space range of the collaborative robot, generate motion control instructions based on the avoidance parameters, and send the motion control instructions to a motion control system of the collaborative robot, and the motion control system is configured to adjust physical driving signals applied to joint motors based on the motion control instructions so as to drive mechanical links of the collaborative robot to generate compound motions to enable an end effector to finish. The method comprises the steps of obtaining monitoring data of a working area of a cooperative robot, determining collision risk values based on the monitoring data, a first motion track of an operator and a second motion track of the cooperative robot, determining avoidance parameters of the cooperative robot based on the monitoring data, the first motion track, the collision risk values, collision urgency and a moving space range of the cooperative robot, generating motion control instructions based on the avoidance parameters, and sending the motion control instructions to a motion control system of the cooperative robot, wherein the motion control system is configured to adjust physical driving signals applied to joint motors based on the motion control instructions so as to drive mechanical links of the robot to generate compound motions to enable end effectors to finish cooperative avoidance. The invention comprises a computer readable storage medium, wherein the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the man-machine collaborative monitoring method based on the sensor. The method has the advantages that (1) a complete and closed-loop man-machine cooperative safety monitoring flow is established, prospective risk assessment is achieved through multi-source perception and track prediction, collision is effectively prevented, interruption to the operation flow is reduced to the maximum extent, safety and overall operation efficiency of man-machine cooperation are remarkably improved, (2) the movement track of an operator in the future period is predicted by using first state data of the operator at the current moment and preset state data of the future period through a sequence prediction m