Evaluation of a boxwood topiary trimming robot

This paper describes a new robot specifically developed for topiary trimming and evaluates its performance through a novel evaluation method. Experiments were carried out in a real garden letting the robot trim spherical-, cylindrical- and cuboid-shaped boxwood topiaries. The robot's performance was evaluated using a quantitative evaluation method, which made accurate 3D point clouds of the bush before and after trimming using photogrammetry. For each point in these point clouds, the Euclidean distance to the ground-truth shape was calculated and classified as correctly trimmed (CT) when the distance was within 2 cm of the ground-truth shape. Using this information the percentage of CT points before and after trimming were compared. Results show a reasonable robot accuracy when trimming spherical topiaries, reporting a 24 percentage point increase of CT points, going from 27% (before) to 51% (after) trimming of the bush surface. Cylinders and cuboids had a lower performance, which reported an increase of CT between −0.2 and 6 percentage point. The performance of the robot was also qualitatively assessed by human observers by scoring topiaries. The highest score of a single bush is a 3.1 out of 5. These results, combined with the quantitative evaluation show that the robot can trim autonomously, but it does not reach the required accuracy for practical application. Despite this, the evaluation method was able to reveal main bottlenecks of the robot in real-world experiments. Together with the robot description, this paper can be used as a guideline for the development and evaluation of gardening robots.