MushR – A Smart, Automated and Scalable Indoor Harvesting System for Gourmet Mushrooms

Idea and relation to VEDLIoT

The MushR project aims to close the gap between the usage of digital tools and modular, adaptable micro-farming and agricultural systems. It introduces four innovative novelties extending the state of the art of gourmet mushroom production, facilitating process automation, more sustainable mushroom provision, increased yield and improved quality of harvested mushrooms. The project proposes a modular and scalable gourmet mushroom growing and harvesting system using an image recognition setup that detects when and which mushrooms are ready to be harvested in combination with an automated mushroom harvesting mechanism for harvesting the mushrooms. Our digital framework solution gathers data from a sensor array responsible for monitoring the agricultural products and an assessment function, which provides the necessary knowledge to adjust the automated cultivation hub.

MushR will contribute to the VEDLIoT ecosystem extension with mainly 3 aspects:

  1. It will enable the usage of the developed tools and strategies to design new, innovative technologies based on the provided input. Since the project is targeted to enhance the image recognition of agricultural (in MushR mushrooms) products, the estimated results could enhance models nowadays in terms of organic structure recognition. They will provide a good approach to monitoring growth rate, recognizing diseases and harm to organic surfaces, and the overall condition of the products.
  2. The planned framework for the digital twin of the farming hub provides a framework that is scalable and transferable to other application domains and enables, therefore, usage in other projects, especially in tasks where environmental monitoring is required.
  3. The implementation of an automated harvester is planned after the conduction of the VEDLIoT project in order to cut the Mushrooms when they reach their harvest date and to integrate a “care tool” in order to boost the growth of the fungi at optimum conditions. Therefore, the different software tools developed within the project can be used for further usage after finishing the task and can be seen as a “Caretaker” platform for organic plant and fungi food products.


  1. Set up a mushroom growth chamber incl. a growth chamber control system, and test the system via the traditional cultivation of mushrooms. Subsequent integration of sensors and cameras for subsequent work packages. The result is a functioning mushroom growth chamber setup, including sensors and cameras.
  2. Design and build reusable mushroom pods for the project and subsequent implementation of a digital twin for the mushroom pods.
  3. Creating a dataset that incorporates images of mushrooms in various growth stages from the camera, sensor data time series from the sensor array as well as growth chamber control inputs to produce a trained model to detect the growth status of a particular mushroom pod. Processing operations are performed on the t.RECS.
  4. Develop, set up and integrate an automated mushroom harvesting mechanism to harvest the mushroom from the mushroom pods. The harvesting mechanism is controlled by the t.RECS.
  5. Evaluating the accuracy of the mushroom growth status detection and performance as well as the quality of the automated mushroom harvesting mechanism in combination with reusable mushroom pods and their digital twin. Moreover, a project report as well as a scientific open access publication (e.g. in MDPI Sensors or MDPI Sustainability or at the AgriTech 2023) will detail the findings of this project and make them available to the funding party and the public for dissemination purposes.


The mushrooms are grown in a sensor-array controlled growing chamber similar to traditional industrial mushroom farms. However, instead of using non-reusable plastic bags, the mushrooms – for the MushR project, we will use an Oyster mushroom strain from our existing mushroom growing setup – are grown in reusable mushroom pods, which are linked to a digital twin for each pod. The growth status and the health of the mushrooms are regularly checked via cameras. The camera input is processed by a YOLO model to detect whether the mushrooms are ready to be harvested or not. The later integrated automated harvesting system will then be activated towards carrying out its task. Finally, the mushrooms are ready for consumption, and the mushroom pods remain in the growing chamber. The data gathered by the sensor array is processed and stored (in an attached data storage) via the VEDLIoT t.RECS, which also takes care of the YOLO-based harvest status prediction and the actual harvesting process.

Besides the automated harvesting mechanism, subsequent research, i.e., future work, may optimise the growth environment parameters to maximise mushroom growth and harvest based on collected sensor data and the digital twin/shadow data of previously harvested mushroom pods. Further, the conception of the hub prototype and the automated harvesting system will be conducted in follow-up research projects to put the designed software system to use. This will allow the testing of the concept on automated agricultural facilities and enable the research work transfer to other branches.

Beyond the production of gourmet mushrooms, the solutions, e.g., growth/harvest monitoring and detection, and the robot-based harvesting developed in MushR, may be generalised to other indoor farming activities in controlled environments beyond mushrooms and in special cases, even for outdoor farming activities.

Expected Impact

MushR aims for a modular and scalable gourmet mushroom growing and harvesting system that extends the state of the art by introducing a novel image recognition system that detects when and which mushrooms are ready to be harvested in combination with an automated mushroom harvesting mechanism.

The results will be delivered in a project report and an open-access publication. Moreover, MushR will design and produce four innovative novelties: Reusable mushroom pods, an AI/ML model to determine the growth status of oyster mushrooms and predict when to harvest the mushrooms, and an automated mushroom harvesting mechanism for oyster mushrooms in reusable mushroom pods.

Further info/links

Project-Info: Link

Live-Stream: Link