Robot man-machine interaction method

Abstract

The invention belongs to the technical field of robot active visual perception, language interaction, radar obstacle avoidance and deep learning, and particularly relates to a robot man-machine interaction method. The robot man-machine interaction method comprises the steps of shooting an RGB image and a depth map of an environment, detecting obstacle information to obtain a laser radar array, performing normalization processing on the obtained data, and constructing a problem coding network in man-machine interaction to code a problem; constructing an image feature extraction network, extracting RGB image and depth image information into a feature matrix, and splicing the laser radar data, the problem codes and the feature matrix to obtain a feature fusion matrix; adopting a convolutional network to obtain a data fusion matrix as a data fusion matrix of the surrounding environment; and training a recurrent neural network as a navigator, taking the data fusion matrix as input, outputting a navigation result, and controlling the motion direction of a robot. According to the method, the functions of self-navigation, self-exploration, man-machine interaction and the like of the robot are realized, and the intelligence of the robot is improved.

Description

technical field [0001] The invention belongs to the technical fields of robot active visual perception, language interaction, radar obstacle avoidance and deep learning, and in particular relates to a robot human-computer interaction method. Background technique [0002] Today, autonomous robots can operate independently to complete specific tasks without human intervention. Autonomous locomotion, a major attribute of autonomous robots, depends primarily on accurate motion estimation and high-level environmental perception. However, in some cases, artificial landmarks are unknowable, or the robot is in a GPS-missing environment, so that ego motion estimation or obtaining scene information encounters great difficulties. Technically, the mobile robot gradually constructs a map consistent with the overall environment by sensing the environment, and at the same time uses this map to realize self-positioning. For a long time, robot navigation problems have been basically solved...

AI Technical Summary

Problems solved by technology

Although they have made great achievements in computer vision and navigation, there is not much progress in the fusion of vision and LiDAR information for map-free navigation, and there are few studies on using the above information for navigation and knowledge question answering.

Images