View Chapter

Chapter 56 — Robotics in Agriculture and Forestry

Marcel Bergerman, John Billingsley, John Reid and Eldert van Henten

Robotics for agriculture and forestry (A&F) represents the ultimate application of one of our society’s latest and most advanced innovations to its most ancient and important industries. Over the course of history, mechanization and automation increased crop output several orders of magnitude, enabling a geometric growth in population and an increase in quality of life across the globe. Rapid population growth and rising incomes in developing countries, however, require ever larger amounts of A&F output. This chapter addresses robotics for A&F in the form of case studies where robotics is being successfully applied to solve well-identified problems. With respect to plant crops, the focus is on the in-field or in-farm tasks necessary to guarantee a quality crop and, generally speaking, end at harvest time. In the livestock domain, the focus is on breeding and nurturing, exploiting, harvesting, and slaughtering and processing. The chapter is organized in four main sections. The first one explains the scope, in particular, what aspects of robotics for A&F are dealt with in the chapter. The second one discusses the challenges and opportunities associated with the application of robotics to A&F. The third section is the core of the chapter, presenting twenty case studies that showcase (mostly) mature applications of robotics in various agricultural and forestry domains. The case studies are not meant to be comprehensive but instead to give the reader a general overview of how robotics has been applied to A&F in the last 10 years. The fourth section concludes the chapter with a discussion on specific improvements to current technology and paths to commercialization.

Autonomous orchard tractors

Author  John Reid

Video ID : 26

Mowing and spraying are two common tasks in orchard environments that require the use of tractors. These tasks take significant time and resources and spraying, in particular, can be dangerous for the operators, all of which suggest benefits from their automation. This video shows two John Deere tractors driving autonomously in an orange orchard. The first tractor is performing a spraying task, using the perception sensors for obstacle detection and to control the amount of spray applied to the trees, such that each tree receives only the minimum amount of chemicals necessary for its size. The second tractor is performing a mowing task, keeping the grass short to improve access to the orchard and reduce competition for resouces with the trees.

Autonomous orchard vehicle for specialty-crop production

Author  Sanjiv Singh, Marcel Bergerman

Video ID : 91

In the United States, production of specialty crops (fruits and vegetables, tree nuts, dried fruits and horticulture and nursery crops, including floriculture) is very labor-intensive. The autonomous orchard vehicle presented in this video can be used year-round to automate tasks such as mowing, spraying, scouting for disease or insects, and estimating crop yield; or to augment humans for pruning, thinning, training trees, placing pheromone dispensers, and harvesting. Studies by the extension teams at The Pennsylvania and Washington State Universities report an increase in efficiency of up to 116% when workers perform operations on the upper part of trees onboard the vehicle, as compared to workers using ladders.

Autonomous utility vehicle - R Gator

Author  John Reid

Video ID : 93

The John Deere R Gator is an unmanned ground vehicle capable of operating in urban and off-road terrain with a large payload capacity to carry supplies or a marsupial robot. The R Gator can operate in teleoperation mode, waypoint navigation, direction drive, and path playback. The perception system on the vehicle is able to detect both positive and negative (holes) obstacles in off-road terrain and is capable of driving through tall vegetation while maintaining safety. The remote operator is able to send commands to the R Gator wirelessly, through an intuitive, video game-style, wearable interface, and can see video and telematics from the R Gator in a heads-up display. This video shows the R Gator performing various missions in off-road terrain in a surrogate agricultural environment. Screen shots from the operator display are shown, including an overhead map with waypoint path visible, video views available to the operator, and telematics. The video also shows the R Gator detecting and avoiding fence posts and a negative obstacle, both of which are quite common in orchards.

Automatic plant probing

Author  Guillem Alenya, Babette Dellen, Sergi Foix, Carme Torras

Video ID : 95

This is a video showing the automatic probing of plant leaves (to measure chlorophyll) with a robotic arm, using a time-of-flight camera and a spadmeter, which are mounted on top. The first part shows plant probing during the final experiments of the EU project GARNICS, performed with a KUKA robot of the Forschungszentrum Juelich. The second part shows probing with a WAM arm at the Institut de Robotica i Informatica Industrial.

VisualGPS – High accuracy localization for forestry machinery

Author  Juergen Rossmann, Michael Schluse, Arno Buecken, Christian Schlette, Markus Emde

Video ID : 96

Developments in space robotics continue to find their way into our everyday lives. These advances, for instance, include novel methods to increase localization accuracy in determining one's position in comparison to conventional GPS systems. The example here is the "VisualGPS" approach that helps to estimate the position of forestry machinery, such as harvesters in the woods, with high accuracy. For "VisualGPS", harvesters are equipped with laser scanners. The sensors scan the surrounding area to generate landmarks from the tree positions. The tree positions are combined into a local, single-tree map. By comparing the local, single-tree map with a map generated from aerial survey data, the current machine position can be calculated with an accuracy of 0.5 m.

Smart Seeder: An autonomous high-accuracy, seed planter for broad-acre crops

Author  Jay Katupitiya

Video ID : 131

This video shows highly accurate (within 2 cm) guidance of a tractor and an implement. The tractor is speed-controlled and follows a specified path very accurately. The implement is a seed planter which also follows the same path with the same accuracy. The implement has its own power unit. Its wheels are steerable and driven under force control as demanded by the force sensor at the hitch point. This relieves the tractor from having to pull the implement with full force, and hence it can be a smaller machine. Highly precise planting and path- following repeatability enables plant-level care which significantly reduce the chemical use, hence reducing adverse environmental effects and cost.

A robot for harvesting sweet peppers in greenhouses

Author  Jochen Hemming, Wouter Bac, Bart van Tuijl, Ruud Barth, Eldert van Henten, Jan Bontsema, Erik Pekkeriet

Video ID : 304

This video shows robotic harvesting of sweet-pepper fruits in a commercial Dutch greenhouse in June 2014. The base of the robot consists of two carrier modules. On the first are located the manipulator (nine degrees-of-freedom), specifically developed for this project, the control electronics and the computers. On the sensor carrier module, two 5 megapixel color cameras (comprising a small baseline stereo setup) and a time-of-flight (TOF) camera are installed. Around the sensors, a light grid is placed to illuminate the scene. The sensor system is mounted on a linear motorized slide and can be horizontally moved in and out of the workspace of the manipulator. Machine-vision software localizes ripe fruits and obstacles in 3D. Two different types of end-effectors were designed and tested. The fin-ray gripper features a combined grip and cut mechanism. This end-effector first grips the fruit and after that the peduncle of the fruit is cut. The lip-type end-effector first stabilizes the fruit using a suction cup after which two rings enclose the fruit and cut the peduncle of the fruit. Both end-effectors have a miniature RGB and a TOF camera for refining the fruit position and to determine the fruit pose. This robot demonstrator is one of the results of the EU project CROPS, Clever Robots for Crops (www.crops-robots.eu).

Ladybird: An intelligent farm robot for the vegetable industry

Author  James Underwood, Calvin Hung, Suchet Bargoti, Mark Calleija, Robert Fitch, Juan Nieto, Salah Sukkarieh

Video ID : 305

This video showcases the Ladybird, an intelligent robot for the vegetable industry. Ladybird provides a flexible platform for sensing and automating commercial vegetable farms. The solar-electric powered vehicle has a flexible drive system that allows precise motion in potentially tight environments, and the platform geometry can be configured to suit different crop configurations. The vehicle autonomously traverses the farm, gathering data from a variety of sensors, including stereo vision, hyperspectral, thermal, and LIDAR. The data is processed to provide useful information for the management and optimization of the crop, including yield mapping, phenotyping, and disease and stress detection. Ladybird is equipped with a manipulator arm for a variety of mechanical tasks, including thinning, weeding (especially of herbicide-resistant weeds), spot spraying, foreign body removal and to support research towards automated harvesting.

An automated mobile platform for orchard scanning and for soil, yield, and flower mapping

Author  James Underwood, Calvin Hung, Suchet Bargoti, Mark Calleija, Robert Fitch, Juan Nieto, Salah Sukkarieh

Video ID : 306

This video shows an end-to-end system for acquiring high-resolution information to support precision agriculture in almond orchards. The robot drives along the orchard rows autonomously, gathering LIDAR and camera data while passing the trees. Each tree is automatically identified and photographed. Image classification is performed on the photos to estimate flower and fruit densities per tree. The information can be stored in a database, compared throughout the season and from one year to the next, and mapped and displayed visually to assist growers in managing and optimizing production.

A mini, unmanned, aerial system for remote sensing in agriculture

Author  Joao Valente, Julian Colorado, Claudio Rossi, Alex Martinez, Jaime Del Cerro, Antonio Barrientos

Video ID : 307

This video shows a mini-aerial robot employed for aerial sampling in precision agriculture (PA). Issues such as field partitioning, path planning, and robust flight control are addressed, together with experimental results collected during outdoor testing.