Benjamin Nicholls

University of Lincoln

Research Interests

Human-robot interaction, machine learning and soft robotics

Presentations

“AI cleaning of unstructured soil data” (poster) – AgriFoRwArdS CDT Annual Conference 2024: Robots in Action [July 2024] – Norwich, UK.
“Domain Generalisation for plant/weed detection” (oral) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.
“AI cleaning of unstructured data for application in models trained on lab-derived and clean datasets” (poster) – AgriFoRwArdS CDT Summer School: Robotic Phenotyping [July 2024] – Wageningen, The Netherlands.
“The AgriFoRwArdS CDT Summer School – Responsible adoption (Theme 3) & Phenotyping Perception beyond 2D Colour (Theme 6)” (oral) – Towards Autonomous Robotic Systems (TAROS) 2024 [August 2024] – London, UK.

Activities and Outputs

Represented the AgriFoRwArdS CDT at the University of Lincoln’s stand at CropTec 2023 – showcasing research and communicating with the public [November 2023] – Stoneleigh, UK.
Author of blog article ‘Students attended Croptec 2023‘ (Dec 2023)
Contributor to blog article ‘Peer-to-peer support for the transition to PhD‘ (Mar 2024)
Author of blog article ‘Students visit vertical farming lab‘ (Apr 2024)

About me

I joined the CDT for the opportunity to get exposure to real-world applications of robotics. I’m looking forward to getting to work alongside industry partners to get a better understanding of a problem from the initial concept all the way to the end goal/product.

I studied at the University of Lincoln for my undergraduate degree and I enjoyed it so much here I decided to stay; my favourite aspect of Lincoln is the amount of green spaces there are around the city.

MSc Project

AI cleaning of unstructured data for application in models trained on lab derived and clean datasets

From an image of the ground featuring seeds and some freshly germinated weeds, remove noise, areas of non-interest, and segment areas of interest. The cleaned images are intended for use on a weed seed classifier as part of my PhD project.

PhD Project

Imaging stale seedbeds for weed mapping, monitoring and early season control

Weed detection systems are an active area of research, and several systems are being brought to market to enable targeted spot spraying systems, that can dramatically reduce the amount of herbicide used (and so reduce the environmental and financial costs). However, these systems typically work on weeds after the crop emerges. This is an important short coming for spot spraying because many key herbicides are applied before the crop emerges (called pre-emergent herbicide). In addition, a key use cases of weed detection is to map weed populations over time to assess management strategies and emerging resistance. By the time the crop and weeds have emerged the majority of weed control actions have already been carried out. Thus, a weed detection system that works in crop can only be used to monitor post-control weed populations, greatly reducing the ability to monitor management effectiveness.

This PhD will develop a machine-vision pipeline to detect weeds in the pre-crop fallow period, known as a the stale-seedbed. Successfully detecting and mapping weeds in the stale-seedbed will provide a direct measure of the underlying seed bank (composition, distribution and abundance). The seedbank is the most important measure of long-term weed populations because the seed bank is the only means of long-term persistence for almost all arable weeds.

This PhD will explore different multi-species classification and detection deep learning architectures for use in unstructured arable stale-seedbeds. It will also develop tools to converting weed detections to spatially referenced maps of the seed bank (e.g. visual odometry, sensor fusion), and from there  optimal spraying maps (e.g. probabilistic planning). Data collection and model validation will be carried out in field.

Ben’s PhD project is being carried out under the primary supervision of Dr Shaun Coutts.

EPSRC Centre for Doctoral Training in Agri-Food Robotics: AgriFoRwArdS site title logo image.