Harvesting Robot
Artist Impression
Sweet-pepper crop
in the greenhouse

The objectives of this workpackage are:
1. To inform growers about the results of the project through SWEEPER website, Growers magazines, demonstration and through the Growers Advisory board.
2. To disseminate the public results to the scientific community through contribution to international conferences and through publications in scientific journals.
3. Evaluation and validation of the performance of the developed robot platform and the developed technologies form a business point of view with the aim to ensure easy and fast market penetration of SWEEPER.
4. Regular updating the plan for the dissemination and exploitation of results (PDER)
5. Ensure exploitation of the project results.

 

For an overview of disseminatied material please visit the Dissemination section of this website.

Workpackage leader

Proefstation voor de Groenteteelt – PSKW (BE)

 

This work package is responsible for setting up tests, analysing the results and suggest improvements for each module and the overall system together with feedback from end-users. This will be done using agile development. This means, that many iterations of the main system, with smaller changes in the modules are evaluated continuously instead of testing the full package after a long period of development time only a few iterations. Full dependencies and detailed plans are not entirely addressed at the beginning. Instead, the approach is to start more general and update and synchronize plans and dependencies such that that project partners and end-users have consistent up-to-date information. Depending on the growing season, testing can only be performed in the end-user environment from April to October. During the winter season, testing will be performed under realistic laboratory conditions.

 

Workpackage leader

Wageningen University & Research Centre (NL)

Jochen Hemming

Personal web-page

e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it..

 

 

The sensing work package will deliver a robust pragmatic computer vision package to localize mature yellow and red fruits and its surrounding obstacles. An early milestone will ensure that a basic sensing framework can be tested and thereafter continuously improved after the first few months of the project start. This early stage will be based on results obtained in the CROPS project. For advanced sensing, a Lightfield camera will be added as primary sensing hardware on the end-effector. Basic software will be provided in an early stage and is based on CROPS algorithms adapted to data collected with the new SWEEPER system.  Necessary adjustments to it are made to meet optical and greenhouse’s constraints. Additional advanced computer vision algorithms will be developed to ensure progress in terms of robustness, accuracy and detection rate. To improve detection rates, sensing from the gripper will be performed from multiple viewpoints. Part of these algorithms will be elaborated on the results from the CROPS project.

Workpackage leader

Ben-Gurion University of the Negev – BGU (IL)

From experience we know that robotic harvesting can encounter many problems in practical situations especially in summertime. Therefore a growing strategy will be developed to improve the visibility of the fruits and the accessibility of the fruit in the crop.

The objectives of this WP are to:
1. Determine the effects of different cropping strategies on the suitability for robotic harvesting (crop openness, length of internodes, leaf surface, length fruit stems…)
  a. Selection of the most appropriate varieties
  b. Effect of cultivation technique
  c. Enhancing crop openness and length of internodes by means of climate control 
  d. Altering plant morphology by means of LED lighting
2. Determine the influence of harvesting method on sensitivity for plant diseases and fruit quality.
3. Determine the influence on the yield of all test objects.
4. Evaluation of the test results with the other partners

Workpackage leader

Proefstation voor de Groenteteelt – PSKW (BE)

The framework for software development from CROPS will be utilized to implement the high-level control of the robot. A flowchart describing the high-level functionality of the robot (DLO) will be translated to a state diagram and implemented as a state-machine that administrates the top-level logical flow of control in the robot (UMU). This work package will also be in charge of development of software for intermediate-level control of the manipulator, including basic path planning and obstacle avoidance Motion towards fruit will be guided by sensory (and in particular, visual) feedback from gripper-mounted sensors.  Furthermore, a simple system for mobility control of the robot platform will be developed, including obstacle avoidance.

Workpackage leader

UMEA University – UMU (SE)