Design of a Sensor-based Controller Performing U-turn to Navigate in Orchards

Tree Detection With Low-Cost Three-Dimensional Sensors for Autonomous Navigation in Orchards

“…This paper only focuses on the point cloud processing algorithm. More details on control aspects can be found in [3].…”

“…The tree detection algorithm has been implemented using the C++ and CUDA languages, as well as the openCV and PCL libraries. Moreover, its parameters have been fixed as follows: size of the sample K Sampling = 350000; distance to 3 with µ 1 = 0.5 meter, θ 1 = 1 degree, µ 2 = 0.05 meter, and θ 2 = 0.1 degree. Moreover, the dimension of the density square is K O = 11 and the occupancy threshold T O = 200.…”

“…In the previously mentioned works, the headland navigation is not addressed or simply performed using pure dead-reckoning. In [3], we have presented a navigation strategy and the related controllers allowing to make the robot switch from the current row to the next one. The strategy relies on the position of the trees in both the rows and the headlands.…”

“…From them, it is possible to deduce the lines the robot has to move along to efficiently follow a row. Moreover, in previous works [3], it has been shown that the last trees of the rows can be used as references to navigate in the headlands, i.e., to perform U-turn maneuvers allowing the robot to transition from one row to the next one. Moreover, in commercial orchards, it appears more suitable to use tree trunks as characteristic features for navigation rather than to compute the free space in front of the robot and use it to determine a path, as it is done for example in [4].…”

Visual Predictive Control of Robotic Arms with Overlapping Workspace

“…The autonomous achievement of any of these tasks requires the same capacities for the robotic system: (i) autonomously navigate in an orchard; (ii) detect and localize a set of natural landmarks of interest; (iii) approach the landmarks with some robotic manipulators; (iv) manipulate/interact with the landmarks of interest without damaging them. After addressing the autonomous navigation problem in (Durand-Petiteville et al, 2017;Le Flecher et al, 2017), the focus is now on the landmark approach problem when considering a couple of robotic manipulators embedded on a mobile platform. This topic has already been addressed during the design of systems harvesting cucumbers (Van Henten et al, a https://orcid.org/0000- 0002-2683-8675 2003) or tomatoes (Zhao et al, 2016b).…”