About the Project
The focus for this project is on small unmanned aerial vehicles, or UAVs (sometimes referred to as "drones", though not the military fixed-wing style), in order to provide manoeuvrability within complex and variable spaces, concentrating on agricultural domains, though also applicable to many other domains. The project will entail design and analysis of various jumping and flying mechanisms, construction and evaluation of prototype devices in the lab, and experimental evaluation of successful prototypes with crops in test fields. Application of standard data science and machine learning techniques will be applied to aspects of experimental evaluation, with respect to assessing the improvement in data collection volume and quality obtained with different prototype device designs.
Our interest in this type of jump-start UAV is motivated by the need to provide high-precision sensing for monitoring crops. Insects thrive in gardens and fields, able to manoeuvre in these complex and variable settings, distinguish between different types of plants and recognise particular species that provide nutrition and shelter. Not just garden pests, insects also inspire us to design efficient sensing mechanisms. In order to practice precision agriculture (intelligent farming conducted at the level of individual plants, rather than whole fields), we need to detect features of plants growing closely together—a substantial challenge for traditional robotic sensing, which relies on large robots and cameras to gather broad images and employ machine learning methods to classify elements and distinguish individual plants from neighbours. If we were able to deploy small robots fitted with tiny sensors that could position themselves accurately alongside specific plants, then we would be solving two problems facing agricultural roboticists today: precisely locating individual plants and repeatedly gathering sensor data on the same plant.
Three sets of experiments will be conducted. First, lab-based comparisons of initial device prototypes with respect to energy usage for take-off, distance achieved and position accuracy will be conducted. Second, field-based comparison of device prototypes with respect to different take-off surfaces (e.g. wet vs dry ground) will assess performance in realistic settings. The third set of experiments will deploy our jumping UAV in a test field at the Lincoln Institute for Agri-foot Technology (LIAT) Riseholme (farm) campus to evaluate the accuracy and reliability of the robot to locate and sense the same plant repeatedly, taking off from different surfaces.
The ideal candidate will have an interest in precision agriculture, a knack for mechanical design and computer programming, and be intrigued by a creative approach to problem solving in an interdisciplinary environment. Specific requirements include:
• At minimum, a 2.1 degree in a relevant or related discipline (for example, but not limited to: Physics, Mechanical Engineering, General Engineering, Electronic/Electrical Engineering, Computer Science, Data Science)
• Ability to demonstrate skills and/or experience relevant to the project subject area(s) of interest
• Experience programming in C/C++ or Python
• Evidence of ability to engage in scientific research and to work collaboratively as part of a team
• Excellent communication skills in written and spoken English
To be eligible for a full award a student must have no restrictions on how long they can stay in the UK and have been ordinarily resident in the UK for at least 3 years prior to the start of the studentship (with some further constraint regarding residence for education. For a fees only award, a Student must be ordinarily resident in a member state of the EU, in the same way as UK Students must be ordinarily resident in the UK. For further information regarding residence requirements, please see the regulations: https://www.ukri.org/files/funding/ukri-training-grant-terms-and-conditions-pdf/
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.