AVOS: Using AI to inspect avocados without damaging them

Visual AVOS from Experience Fruit Quality
The Netherlands is one of the largest avocado importers: 415 million kilograms in 2020, an increase of 19% compared to 2019. Avocados are a very popular and indispensable product at a greengrocer’s or in a supermarket. Find out when an avocado is ripe to eat is still a challenge, though.

Pressing, squeezing and feeling avocados until you find one with just the right amount of give to show it is ripe does nothing to improve the quality of the product while generates waste and affecting costs. Recent consumer research has shown that one in three avocados is thrown away.

What challenge does it solve?

Estimating the ripeness of an avocado is a tricky issue much earlier in the logistical chain too. Before an avocado reaches a consumer, it passes at least ten intermediate points. The question is how the ripeness can be estimated during this process without damaging the fruit. Combining the experience of inspectors with new technological possibilities has let Experience Data and its subsidiary Experience Fruit Quality come up with a solution that also has a positive impact, reducing waste and improving cost-efficiency. They developed a smart device called AVOS that lets inspectors see how ripe an avocado is without cutting into it.

Use of artificial intelligence

The revolutionary smart machine AVOS is a practical tool for daily use in the workplace. The smart AI in the machine can perform quality checks better than visual inspections. AVOS collects unique qualitative data, stores that information and then uses AI to estimate the ripeness and quality of avocados. If the system is uncertain about the quality, an employee is called to assess the quality manually.

Impact

Applying the insights from the data and adjusting the core process and working methods make it possible to solve complex issues and improve the operational and strategic core processes. Alternative logistical choices can be made as a result, leading to less waste and lower CO2 emissions. These choices ultimately result in fewer complaints about ripeness and quality. When the entire chain is more transparent thanks to the data and can explain what it has learned, not only the inspectors but also the employees, managers and avocado farmers can make better and smarter decisions. The digital assistant AVOS is perceived in this process as a unique colleague who offers clear added value.
As a result of this method:

  • The inspector can now look at larger numbers of avocados based on larger samples and can make smarter and more well-founded decisions about batches based on that data.
  • At the supplier level, managers can see the maturity and quality, detect problems, explain things to suppliers and determine strategic actions based on this information.
  • The management have a clear picture of the global import and transit of avocados, waste reduction and cost savings; they too can make smarter choices to make the chain more sustainable.

The benefits and goals

The primary goal of AVOS is to reduce waste of avocados and save costs by doing so. Additionally, specialist knowledge is permanently recorded. The solution can be optimally integrated into the daily work of avocado inspectors. It consists of the following components: AVOS mini (sensors), AVOS app (software), AVOS AI (models) and AVOS (Avatar). Studies are being carried out into whether it is possible to apply the knowledge acquired to other products such as mangoes. AVOS has now been successfully applied by Albert Heijn and Bakker Barendrecht.

Joint aims

The AVOS device lets Experience Fruit Quality (a subsidiary of Experience Data) focus on a specific market: fruit quality. Experience Data itself focuses on the corporate market. Experience Data’s mission is operationalising AI to make the lives of professionals easier and more fun with smart data solutions for reducing repetitive and complex tasks. Experience Data has accumulated experience and knowledge in AI and data science and is happy to share that knowledge and experience with participants of the NL AIC to assist the further development of AI in the Netherlands.

Collaborative partners

Experience Fruit Quality and Experience Data collaborated in this project with R2R and Sanders Machinebouw. For more information about the development of the AVOS smart machine and the associated application options, please go to the Experience Data or Experience Fruit Quality websites.

Share with

More information

Building blocks

The NL AIC collaborates on the necessary common knowledge and expertise, resulting in five themes, also called building blocks. Those are important for a robust impact in economic and social sectors.

Sectors

AI is a generic technology that is ultimately applicable in all sectors. For the development of knowledge and experience in the use of AI in the Netherlands, it is essential to focus on specific industries that are relevant to our country. These industries can achieve excellent results, and knowledge and experience that can be leveraged for application in other sectors.

    Become a participant

    The Netherlands AI Coalition is convinced that active collaboration with a wide range of stakeholders is essential to stimulate and connect initiatives in Artificial Intelligence. Within fields of expertise and with other stakeholders in the ecosystem to achieve the most significant result possible in the development and application of AI in the Netherlands. Representatives from the business community (large, small, start-up), government, research and educational institutions and civil society organisations can participate.
    Interested? For more information, see the page about participation.