Binocular visual sense based intelligent obstacle avoidance algorithm

Abstract

The invention discloses a binocular visual sense based intelligent obstacle avoidance algorithm. The algorithm comprises the following steps that S1) a route is planned according to a destination of arobot, left and right cameras of a binocular camera are calibrated, and plane equations of the ground in coordinates of the left and right cameras are calculated respectively; S2) the binocular camera collects an image in front of the robot, and the image is de-noised; and S3) distortion and polar lines in the two images collected by the left and right cameras of the binocular camera are corrected, distortion is eliminated, matching points are limited in one straight line, and finally, a parallax image is obtained by matching. The algorithm satisfies the requirement for detecting barriers correctly in high precision, the requirement of real-time detection can be met, the accuracy and instantaneity are both taken into consideration, and the robot achieves a good obstacle avoidance effect.

Description

technical field [0001] The invention relates to the field of intelligent obstacle avoidance, in particular to an intelligent obstacle avoidance algorithm based on binocular vision. Background technique [0002] During the actual operation of the mobile robot, most of them are in a dynamic uncertain environment. In this environment, the operating environment of the robot is partially unknown, and some obstacles in the working environment are dynamically uncertain; In the environment of obstacles, it can only be solved by online local path planning. At present, the commonly used obstacle avoidance methods include fuzzy navigation algorithm, artificial potential field algorithm, rolling window algorithm, etc. However, these intelligent control algorithms do not have the function of dynamic prediction. , the obstacle avoidance effect on fast-moving dynamic obstacles is poor. Therefore, in the existing technology, the prediction function is added to the obstacle avoidance algori...

AI Technical Summary

Problems solved by technology

[0002] During the actual operation of the mobile robot, most of them are in a dynamic uncertain environment. In this environment, the operating environment of the robot is partially unknown, and some obstacles in the working environment are dynamically uncertain; In the environment of obstacles, it can only be solved by online local path planning. At present, the commonly used obstacle avoidance methods include fuzzy navigation algorithm, artificial potential field algorithm, rolling window algorithm, etc. However, these intelligent control algorithms do not have the function of dynamic prediction. , the obstacle avoidance effect on fast-moving dynamic obstacles is poor

Therefore, in the existing technology, the prediction function is added to the obstacle avoidance algorithm to improve the accuracy of dynamic obstacle avoidance, and the commonly used prediction methods include time series method, regression analysis method, gray prediction method, etc. In the analysis of causality regression model and time series model, the established model cannot comprehensively and essentially reflect the internal structure and complexity of the predicted dynamic data, thus losing the amount of information

Images