Cloud robot collaborative learning method based on hybrid enhanced intelligence

Abstract

The invention provides a cloud robot collaborative learning method based on hybrid enhanced intelligence. The method comprises the following steps of S1, adopting a meta-learning method of NTP (NeuralTask Programming) for dividing a large task recursion into simple sub-tasks for teaching robots; S2, achieving robot action imitative learning based on a human-computer interaction technology, and teaching the robots about skills; S3, utilizing a self-organizing incremental neural network (SOINN) to gather the scattered robot skills for sharing use. According to the method, multiple robots learnhuman skills separately, then upload learned information into a server and share the information in the server for training and adjustment. Not only can the learning time be greatly shortened, but also the diversity of tasks can be expanded. The robots conduct collaborative learning and transmit experiences to one another through a network (or a cloud robot), that is to say, the robots can learn from one another.

Description

technical field [0001] The invention relates to the field of human-computer interaction, in particular to a cloud robot collaborative learning method based on hybrid enhanced intelligence. Background technique [0002] At present, the main application fields of human-robot collaboration include industrial robots, home service robots, medical robots, rescue robots, and special robots, etc. These fields usually require human participation and leadership to complete relatively complex tasks. In the past, robots often completed some rough tasks first, and then workers completed other difficult and complex tasks on the next assembly line. However, this mode wastes a lot of production time, because some tasks can be completed at the same time; On the one hand, in some tasks, workers can complete tasks more efficiently with the assistance of robots or robots with the assistance of workers. In these production lines, robots can complete some tedious and heavy work, while workers ca...

AI Technical Summary

Problems solved by technology

However, if you want a robot to master multiple skills and adapt to multiple environments, you should not train each skill in each environment from scratch, but need the robot to learn how to learn multiple new skills by reusing previous experience. task, so we should not train each new task independently

Images