In recent years, autonomous robots have been gradually introduced into various agricultural operations to address the ever-increasing labor shortage problem. Accurate navigation from one row to another is one of the many challenging tasks for an autonomous robot scouting in semi-structured agricultural fields. In this study, a marker-based row alignment control is proposed for the cross-bed motion of a scouting robot in strawberry fields. Specifically, a feature-based computer vision algorithm is used to detect primitive markers placed at the end of each planting bed. Then the image coordinates of detected markers are used to guide the robot to move away from one row and then align with the next one. The proposed method is low cost and robust with respect to varying lighting conditions, and has been validated in a local strawberry farm.

SummaryRecently, autonomous field robots have been investigated as a labor-reducing means to scout through commercial strawberry fields for disease detection or fruit harvesting. To achieve accurate over-bed and cross-bed motions, it is preferred to design the motion controller based on a precise dynamic model. Here, a dynamic model is developed for a custom-designed strawberry field robot considering terramechanic wheel–terrain interaction. Different from existing models, a torus geometry is considered for the wheels. In order to obtain a control affine model, the longitudinal force is curve-fitted using a polynomial function of the slip/skid ratio, while the lateral force is curve-fitted using an exponential function of both the slip/skid ratio and slip angle. An extended Kalman filter (EKF) is then developed to estimate the unknown parameters in the approximated model such that the state variables propagated by such a model can match experimental data. The approximated model and the EKF-based parameter estimation method are then validated in a commercial strawberry farm.

Autonomous plant alive status monitoring and corresponding localization of individual plant are two important tasks in precision agriculture. In this study, two new methods that are crucial to such robotic operations are proposed. First, a low cost and light scene invariant approach is proposed to differentiate green and yellow leaves using distinct color-ratio index ranges. Second, based on the relative pixel information of neighboring plants, an extended Kalman filter is used to determine plant positions. Such a differential style localization method is shown to be capable of achieving a similar centimeter level accuracy as light detection and ranging (LIDAR) or real-time kinematic-global positioning system (RTK-GPS) based approaches, but with a much lower upfront and maintenance cost. These two new methods are successfully validated in a nearby commercial field.

When conducting precision operations, such as disease detection, weed removal, yield prediction, and harvesting, on plants such as strawberries and blueberries, it is necessary to know the exact location of each plant. To date, GPS and LiDAR based methods have been proposed, however these methods either cannot routinely store position data, are labor intensive, expensive, or bulky. In this study, a low cost and lightweight localization approach is proposed using relative pixel information of adjacent plants. The kinematic information of a scouting robot carrying the camera and the relative position information of adjacent plants are modeled. The centroids of strawberry plants are identified one by one via image processing technologies. An extended Kalman filter is then developed to estimate the relative positions of adjacent plants. The proposed strawberry plant localization algorithm is validated in a commercial farm. The method is low cost and can be used in routine localization operations in agricultural fields.