Obstacle avoidance robot based on visual feature binding and reinforcement learning theory

Abstract

The invention discloses an obstacle avoidance robot based on visual feature binding and a reinforcement learning theory. Visual feature binding and the reinforcement learning theory are utilized, and depth image information is integrated to learn priori knowledge of complex environment on the basis of a convolutional network and image matching technology; on the basis of a feature binding mechanism, a result is fed back to obstacle avoidance of the obstacle avoidance robot to make a decision intelligently, quickly, efficiently and accurately; an MNIST handwriting dataset is adopted, different control signal meanings are given to numbers 0-9 respectively, a Kinect sensor is utilized to collect RGB images with moving distance containing handwriting pictures in the complex environment, and an image matrix is created and output through gray-scale processing; image matching is performed, pictures after being matched are subjected to binarization processing and substituted into a well-trained image recognition model based on a convolutional neutral network, numbers in front of the sensor are judged finally, and corresponding control signals are transmitted to a robot control module through a host to realize intelligent obstacle avoidance.

Description

1. Technical field [0001] The present invention is an obstacle avoidance robot based on visual feature bundling and reinforcement learning theory. The invention utilizes visual feature bundling and reinforcement learning theory, based on convolutional network and image matching technology, fuses depth image information, and learns prior knowledge of complex environments. Feature bundling mechanism, and feed back the results to the obstacle avoidance of the obstacle avoidance robot, making decisions intelligently, quickly, efficiently and accurately. 2. Background technology [0002] In order to realize the application of visual feature bundling theory in real life, try to provide cognitive basis and reference model for machine intelligence, the present invention is based on PCNN-based visual image segmentation technology, convolutional neural network (CNNs) model, image based on grayscale On the basis of basic theoretical methods such as matching technology and image recogni...

AI Technical Summary

Problems solved by technology

Of course, how to quickly capture, measure distances in real time, and provide timely feedback is a complicated application process

Images