Development of a prototype robot and fast path-planning algorithm for static laser weeding

Abstract

To demonstrate the feasibility and improve the implementation of laser weeding, a prototype robot was built and equipped with machine vision and gimbal mounted laser pointers. The robot consisted of a mobile platform modified from a small commercial quad bike, a camera to detect the crop and weeds and two steerable gimbals controlling the laser pointers. Visible class one laser pointers were used to simulate the power laser trajectories. A colour segmentation algorithm was utilised to extract plants from the soil background, size estimation was used to differentiate crop from weeds and an eroding and dilating algorithm was developed for objects that were touching. Conversely, another algorithm, which relied on shape descriptors, was able to distinguish plant species in non-touching status regardless of area difference. To reduce route length and run time, a new path-planning algorithm for static weeding was proposed and tested. It was demonstrated to be more temporally efficient especially when addressing higher density of weeds. A model to determine the optimal segmentation size based on time taken for treatment was established. It was found that the segmentation algorithm has the potential to be widely used in fast path-planning for the travelling-salesman problem. Finally, performance tests showed that the weeding mean error was 1.97 mm, with a 0.88 mm standard deviation. Another test indicated that with a laser traversal speed of 30 mm/s and a dwell time of 0.64 s per weed, it had a hit rate of 97%.

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

“…The systems full integration enables the robot to harvest continuously along the strawberry rows. The overall sequence is termed static strawberry harvesting, because the platform will stop, carry out picking operation and then move on when picking is finished, which is similar to the sequences of other agricultural robots (Xiong et al, ). The hardware and software architecture of the robot is shown in Figure , in which the outside hexagons represent the hardware modules while the inside rectangles are the software functions.…”

Robotic weed control using automated weed and crop classification

“…Automated weed control, including weed detection and removal, has gained significant popularity in the community of precision farming over recent years (Bechar & Vigneault, 2017; Fennimore, Slaughter, Siemens, Leon, & Saber, 2016), due to its great potential to improve the weeding efficiency while reducing the environmental and economic costs. Many robotic weed control systems have been proposed with focuses primarily on single tactics (Slaughter, Giles, & Downey, 2008): selective chemical spraying (Lee, Slaughter, & Giles, 1999), mechanical weeding (Pannacci, Lattanzi, & Tei, 2017), flaming (Datta & Knezevic, 2013), and electrical discharging (Blasco, Aleixos, Roger, Rabatel, & Molto, 2002; Vigneault & Benoît, 2001; Xiong, Ge, Liang, & Blackmore, 2017). However, the study (Kunz, Weber, Peteinatos, Sökefeld, & Gerhards, 2018) indicates that a combination of tactics could maximize weeding performance, named integrated weed management (Chikowo, Faloya, Petit, & Munier‐Jolain, 2009; Young, 2018).…”

Path Tracking Control of Field Information-Collecting Robot Based on Improved Convolutional Neural Network Algorithm

“…To this end, a new type of deep adversarial convolutional neural network can be used [17]. Through picture recognition, the robot can detect the obstacles [18], then avoid the obstacles and a desired path can be planned [9,19], so as to realize the robot's moving and turning in the field environment.…”

“…To this end, a new type of deep adversarial convolutional neural network can be used [17]. Through picture recognition, the robot can detect the obstacles [18], then avoid the obstacles and a desired path can be planned [9,19], so as to realize the robot's moving and turning in the field environment.As a crop widely planted in China, corn often suffers from plant diseases and insect pests in the middle and late stages of its growth, mainly because it has a high-stalk type, growth higher in the middle and late stages, and lacks sufficient light as it is often shaded by leaves and branches. Such conditions make it difficult to be recognized by conventional visual technology.…”