Vision-based guidance control scheme for autonomous navigation of 4WDS agricultural vehicle in a narrow space environment

摘要

This paper proposes a feature-based tracking scheme based on machine vision for use in four-wheel drive/steering (4WDS) agricultural robot navigation. The fusion of robot attitude information and an image extraction technique is utilized to estimate the center of gravity of crops and the heading of the robot. Meanwhile, the steering angle and velocity of each wheel of the robot are regulated through fuzzy logic and a proportional-integral-derivative (PID) control method in order to achieve crop row navigation in a narrow space environment. Experiments have been conducted to demonstrate the effectiveness and practicality of the proposed scheme.