HEADLAND TURNING MANEUVER OF AN AUTONOMOUS VEHICLE NAVIGATING A CITRUS GROVE USING MACHINE VISION AND SWEEPING LASER RADAR
This article discusses the development of row to row turning maneuver of an autonomous vehicle at the headlands of citrus groves. A turning maneuver is executed in a series of five steps which are 1) determining the approach of the end of the current row, 2) establishing the end of the row, 3) turning into the headland, 4) turning into the next row, and 5) getting to a position to navigate the next row. A John Deere eGator was used as the autonomous vehicle. The sensors used for executing the maneuver are video camera, laser radar (ladar), inertial measurement unit (IMU), and wheel encoder. The video camera and the ladar aid in detecting and navigating the headland. The sweeping ladar aids in accurately determining the end of the row. The yaw angle measured by the IMU provides the vehicle-turning angle, and the wheel encoder is used for speed control and dead reckoning to confirm end of row. The headland turning maneuver of the vehicle was tested in a citrus grove. Performance measures of the vehicle, while executing the maneuver, are reported. Headland turning ability combined with row navigation ability enables an autonomous vehicle to completely navigate a citrus grove.
Subramanian, V. and Burks, T.F. (2009). HEADLAND TURNING MANEUVER OF AN AUTONOMOUS VEHICLE NAVIGATING A CITRUS GROVE USING MACHINE VISION AND SWEEPING LASER RADAR. Acta Hortic. 824, 321-328
guidance, sensor fusion, image processing, camera, encoder, control, steering