John Billingsley

The successful development of a vision guidance system for agriculture

Abstract In a project which has lasted 3 years, a vision guidance system has been developed to the stage where commercial availability is imminent. Six prototypes have been field tested by farmers and two more are on trial in the United States. There have been several changes of technology but the fundamental principles have remained consistent. The system derives its guidance signal from a video camera image of the rows of a crop such as cotton. It is relatively insensitive to additional visual ‘noise’ from weeds, while tolerating the fading out of one or more rows in a barren patch of the field. The software integrates data from several crop rows, and tests each row for image quality. Colour components of the image signal can be selected to improve discrimination between crop and detritus. Experimental results are presented showing that the system is capable of maintaining an accuracy of 2 cm. Some farmer responses from the extensive field trials are also included.

Vision-guidance of agricultural vehicles

A vision guidance system has been designed, built and commissioned which steers a tractor relative to the rows of a crop such as cotton. It was required to be insensitive to additional visual “noise” from weeds, while tolerating the fading out of one or more rows in a barren patch of the field. The system integrates data from several crop rows, testing for image quality. At the same time, the data processing requirements have been limited by the use of frame-sequential strategies to reduce the image space which must be processed. The design has been developed to the stage where six evaluation prototypes have been installed to test farmer-acceptance. The present prototypes employ a 486 PC motherboard embedded in a custom housing, together with a 68HC11 microcomputer to which the task of closing the steering servo loop is delegated. The system shows great promise for cost effective commercial exploitation.Experimental results are reported and further sensing systems are outlined for performing related guidance tasks when vision is inappropriate.

Robotics in agriculture and forestry

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 LHD loading

Machine vision is used for guidance of the autonomous loading of ore during underground mining. Three dimensional spatial data of the ore pile is derived in real-time from camera images and is used for planning the scooping process. A sensory integration technique combines feedforward from the same vision system with wheel odometry to guide the vehicle to and from the ore pile. A computationally efficient kinematic model of the vehicle is derived and its application discussed. LHD (load-haul-dump) vehicles are used extensively in underground mining. Increasing production costs and the ongoing quest for improved safety provide a great incentive to automate their working cycle. This research concentrates on a major component of this task-automation of loading. The proposed loading controller will load an LHD swiftly and safely while leaving the ore pile in a suitable condition for subsequent bucket scoops.

Mechatronics and machine vision in practice

Proceedings of 13th Annual Conference on Mechatronics and Machine Vision in Practice, Toowoomba, Australia, 5-7 December 2006.

A sensor for the sugar cane harvester topper

A robust low cost refractometer has been developed together with signal conditioning algorithms to enable sucrose content to be measured during the mechanical harvesting of the sugar cane plant. This technology will be applied to the harvester process that removes the tops of the cane to assist the harvester operator to cut the cane at the optimum cutting height.

Using machine vision classification to control access of animals to water

Invasive vertebrate pests together with overabundant native species cause significant economic and environmental damage in the Australian rangelands. Access to artificial watering points, created for the pastoral industry, has been a major factor in the spread and survival of these pests. Existing methods of controlling watering points are mechanical and cannot discriminate between target species. This paper describes an intelligent system of controlling watering points based on machine vision technology. Initial test results clearly demonstrate proof of concept for machine vision in this application. These initial experiments were carried out as part of a 3-year project using machine vision software to manage all large vertebrates in the Australian rangelands. Concurrent work is testing the use of automated gates and innovative laneway and enclosure design. The system will have application in any habitat throughout the world where a resource is limited and can be enclosed for the management of livestock or wildlife.

IEEE Robotics and Automation Society Technical Committee on Agricultural Robotics and Automation [TC Spotlight]

The IEEE Robotics and Automation Society Technical Committee (TC) on Agricultural Robotics and Automation was launched in 2012 with the goal of bringing together researchers and practitioners, academic and industrial, in an informal setting to increase knowledge dissemination in the field. The goal for 2013 is to hold at least eight Webinars and for 2014 to hold one every month. The TC members are rewriting the Handbook of Robotics chapter on Agricultural and Forestry Robotics and wrote an invited chapter on Agricultural Robotics on an SAE book on autonomous vehicles. Beyond endowing machines and vehicles with higher levels of intelligence, two long-term challenges, such as humanlike manipulation of crops and harvesting robots, must be addressed before R&A makes a full incursion into agriculture. Membership in the TC is open to all interested in contributing to the exciting field of agricultural robotics and automation.

Automatic guidance of agricultural mobiles at the NCEA

An outline is given of a vision guidance project, completed and the product brought to market by the National Centre for Engineering in Agriculture, Queensland, and of carrier‐phase GPS methods at an advanced stage of experimentation. These establish an infrastructure for a small autonomous “robot farmhand”.

Measuring the density of dingo teeth with machine vision

Collaboration between a mechatronics engineer and a biologist resulted in an unlikely application of machine vision. To deduce the density of the porous teeth, the volume had to be found. An expedient method was constructed for scanning the teeth before they had to be returned to their source and a simple method was derived for deducing their volume.