Description

Context and research challenge

Growers are expected to increase their fruit production with higher quality at lower expenses in a sustainable way that is less dependent on labour force. By 2050, the agri-food sector must generate 50% more food and feed due to increased demand.[1] Fruit growers need many seasonal workers to perform tedious manual tasks, including pruning, thinning flowers or fruitlets and harvesting. However, society has moved away from living in rural areas to people living in cities now; as a result, agricultural companies are facing the challenge of workforce higher costs or even shortages. The EU agricultural outlook of the European Commission (2018) predicts that labour outflow from the agricultural sector will continue until 2030. The outlook suggests that the agricultural workforce will reach 7.7 million workers in 2030, with a yearly decline of 2% by 2030. The recent new coronavirus COVID-19 outbreak causes a dramatic shortfall in workers because of the border restrictions put in place to stem the spread of the virus. The restriction of the movement of seasonal workers could cause far-reaching and long-term impacts on the agri-food sector and could extend “well beyond this year.”[2] Not to mention that besides a lower availability of seasonal workers, labour costs only increase, which is not compatible with low fruit prices. A promising solution to help with this shortage of workers and high labour costs is the use of agricultural robots integrating Artificial Intelligence (AI).

The main challenges for current state of the art robotics in agriculture include (1) operating in varying and unstructured environments (e.g., occlusion, fruit clustering, changes in canopy and light conditions), (2) assuring operational safety and efficiency, (3) interaction with deformable plants, (4) adequate skill and knowledge required to implement robotic field operations effectively and efficiently[3]. To tackle these challenges, simulation environments and methods can provide an alternative for experimenting with different sensing and end effectors to verify the performance functionality of the robot in such diverse scenarios. This offers a reliable approach to bridge the gap between innovative design and field trials, and therefore can accelerate the development of a robust agricultural robotic platform and the evaluation of novel sensing and control algorithms. Technological advances over the last few years have greatly increased our ability to collect, collate and analyse data on a per-tree basis at large orchard scales. This can also be called a “Digital-Twin Orchard”. A digital-twin is a virtual model of every tree and surroundings. The pairing of the virtual and physical worlds allows analysis of data and continuous monitoring of orchards production systems, and to develop new opportunities for end-to-end learning. Monitoring of orchards is not a new concept but the digital-twin is a continuously learning system that could be queried automatically to analyse specific outcomes under varying simulated environmental and orchard management parameters. So, to avoid expensive redesigns and shorten the critical time to market, virtual prototyping and testing in a virtual digital twin world opens up tremendous opportunities for robotics in agriculture. 

Approach

Drone and tractor based image processing. Use of a stereo camera mounted on a small tractor platform to automatically build depth maps of the orchard, extracting 3D information for structural parameter extraction,  and accurate flower and fruit counting to predict yield.  Information extraction will involve using deep learning algorithms for object detection, building on the deep learning expertise of VITO from other projects.

With this call, we invite researchers to submit their resumé (including track-record) and a one-page project description, that will be the basis for selecting candidates with whom we will collaborate for developing a competitive MSCA-PF proposal. 

 Collaborations

Udl, Lleida, Spain - Pcfruit, St Truiden, Belgium

Deadline application to VITO

Interested candidates should submit their resume (incl. track record) and a one-page note describing the project for which a Marie Curie grant will be applied, as soon as possible and no later than Friday 2 April 2021 17h Brussels time.

Supervisor

 Successful candidates will be supervised by Bart Beusen. Bart has been using deep learning since 2015 on various projects involving satellite, aerial and UAV data.

Bart Beusen – bart.beusen@vito.be/Remote Sensing and Earth Observation Processes/Phone: +3214335843

Deadline MSCA-PF 2021

Wednesday 15 September 2021 17h Brussels time.

Target start date

The EU informs the results on the MSCA-PF applications in February 2022. Successful candidates are expected to be available to start within the following two months and no later than summer 2022.

 

[3] Zhang, Q., Karkee, M. and Tabb A. (2019), The use of agricultural robots in orchard management, in Robotics and automation for improving agriculture, J. Billingsley, Ed. Burleigh Dodds Science Publishing, pp. 187–214. http://dx.doi.org/10.19103/AS.2019.0056.14

Qualification

We invite applicants to propose a more detailed and focused research approach within the scope of this MSCA-PF Fellowship as a part of their application. We are primarily looking for experienced researchers who wish to use this period as an opportunity to further develop their research and skills, and to develop longer-term research collaborations with VITO and other institutions conducting research in the field.

The candidates as in principle must be eligible for a Marie Curie Postdoctoral Fellowship – please refer to the conditions to be set-out in the Horizon Europe MSCA-PF-2021 Work Programme, including taking into account the new MSCA Green Charter principles.

The following assets will be advantageous:

  • An excellent track record in research, necessary for being able to develop a competitive Marie Curie Fellowship application;
  • Already published relevant research work in prestigious scientific journals;
  • An open and cooperation-oriented nature, but with strong abilities for independent research work;
  • highly proficient in spoken and written English.
  • Experience in python
  • Experience in deep learning is an advantage
Offer

Initially, we offer assistance in developing competitive Marie Curie Individual Fellowship proposals.

Then, to successful applicants to the Marie Curie programme, we offer;

  • An exciting opportunity at VITO, the independent Flemish research organisation driven by the major global challenges. Our goal? To accelerate the transition to a sustainable world;
  • Participation in a dynamic professional research & innovation community;
  • Flexible working conditions;
  • An inclusive and friendly work environment;
  • On-boarding assistance and other services.

Requisition

Location: 
Mol
Jobfield: 
Postdoc
ID: 
32484