Man-machine collaboration tool delivery system and method based on teaching learning

Abstract

The invention belongs to the field of artificial intelligence and robot control, and particularly relates to a man-machine collaboration tool delivery system and method based on teaching learning. Theman-machine collaboration tool delivery system includes a mechanical arm, motion capture system positioning points and a PC upper computer. The mechanical arm is a multi-axis mechanical arm with a motion control function, the motion capture system positioning points are attached to a tool and hands of users, a motion capture system is used for obtaining the position of a positioning point, so asto obtain the position of the tool and the hands, and the PC upper computer and the mechanical arm can communicate in real time. The man-machine collaboration tool delivery system is built, based on tail end position data of the mechanical arm collected in the teaching process, the PC upper computer establishes a teaching data set, generates a trajectory probability model, and generates a new trajectory probability model for the change of wrist positions of the users, and the mechanical arm completes a tool delivery task together with people under a control instruction of the PC upper computerto meet the requirements of dynamic trajectory planning.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and robot control, and in particular relates to a teaching-learning-based human-machine collaborative tool delivery system and method Background technique [0002] Processing and manufacturing technology is the core of economic competition. With the continuous enrichment of processing methods, more and more tools are used in the processing process. It is time-consuming and labor-intensive to go to the tool library to get tools to the processing site. Greatly reduces work efficiency. Human-robot collaboration can improve production efficiency and product quality, and is one of the research hotspots in the field of robotics. At the same time, human-machine collaboration can also play a huge advantage in tool delivery. For example, in the working environment, it is possible to predict human behavior and then control the robotic arm to deliver corresponding tools to people, thereby speeding up ...

AI Technical Summary

Problems solved by technology

However, the existing teaching and learning method "imitation learning method based on DMP" is time-dependent, sensitive to time disturbance, and poor in stability; the imitation action of "based on behavior replication (BC) method" is limited to teaching Within the range of motion, the adaptability is poor

Images