Interaction robot intelligent motion detection and control method based on nerve network

Abstract

An interaction robot intelligent motion detection and control method based on a nerve network uses a conventional characteristic engineering and classifier as a human eye portion for primary positioning, the nerve network can carry out behavior high efficiency identification, and a limit state machine is introduced to realize state fast conversion. Stage 1: extracting Haar-like features and combining with an Adaboost cascade classifier to finish interaction robot face identification and face human eye identification, and using a convolution nerve network to carry out human eye secondary detection and screening; stage 2: calculating a dual-eye light flow graph, using CNN to extract spatial domain characteristics, using LSTM to extract time domain characteristics, and finishing human eye behavior identification; stage 3: using the limit state machine FSM to finish state conversion. The system is high in detection precision, and fast in state conversion.

Description

technical field [0001] The invention relates to a behavior detection and motion control method for educational interactive robot personnel. Specifically, the interactive robot camera is used to capture the state of the personnel's eyes (left, right, recovery, etc.) in real time, through face detection, face eye detection, eye position Secondary confirmation, CNN+LSTM eye optical flow map spatio-temporal feature extraction and behavior classification, and finally use finite state machine for motion conversion and control. The interactive robot performs corresponding actions according to the motion state (left arm swing, right arm swing, hand shaking, etc.). This method includes computer vision (behavior recognition), artificial intelligence (policy control) and other fields. Background technique [0002] Interactive robots belong to a branch of robots and play a vital role in the fields of industry, education, and scientific research. By combining the cutting-edge high-tech...

AI Technical Summary

Problems solved by technology

[0003] The existing technology has two difficulties in using eye behavior to control the movement of interactive robots: Difficulty 1, how to detect the eye parts of the pictures captured by the camera in the shortest time, and the correctness and robustness of eye detection directly affect the follow-up behavior of the system The detection process and the execution result of the final motion state, wrong detection or no detection will lead to the failure of behavior analysis; the second difficulty is how to analyze the eye movement according to the time information to determine the interactive human behavior after the eye part is detected, and quickly perform state replacement and exercise execution

The above problems have not yet been resolved

Images